{
  "metadata": {
    "total_size": 10397634954
  },
  "weight_map": {
    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.speech.0.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.speech.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.speech.2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.speech.2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.vision.0.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.vision.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.vision.2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.audio_projection.vision.2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.attn.in_proj_bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.attn.in_proj_weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.ln_k.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.ln_k.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.ln_q.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.ln_q.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_caption.query": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.attn.in_proj_bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.attn.k_proj_weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.attn.q_proj_weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.attn.v_proj_weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.ln_k.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.ln_k.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.ln_q.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.ln_q.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.attn_pool_contrast.query": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.bn.num_batches_tracked": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.bn.running_mean": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.bn.running_var": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.conv_pos.pos_conv.0.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.conv_pos.pos_conv.0.parametrizations.weight.original0": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.conv_pos.pos_conv.0.parametrizations.weight.original1": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.feature_extractor.conv_layers.0.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.feature_extractor.conv_layers.0.2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.feature_extractor.conv_layers.0.2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.feature_extractor.conv_layers.1.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.feature_extractor.conv_layers.2.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.feature_extractor.conv_layers.3.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.final_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.final_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.layer_norm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.layer_norm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.mask_emb": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.post_extract_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.post_extract_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.project_q.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.project_q.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.quantizer.vars": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.quantizer.weight_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ecg_encoder.quantizer.weight_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ln_caption.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ln_caption.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ln_contrast.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.ln_contrast.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.logit_scale": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.audio_embed.encoder.encoder.ecg_encoder.proj_contrast": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.glb_GN": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.embeddings.patch_embedding.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.attention.in_proj_bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.attention.in_proj_weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.attention.out_proj.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.attention.out_proj.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.layernorm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.layernorm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc1.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc1.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.head.probe": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.post_layernorm.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_processor.post_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_projection.0.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_projection.0.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_projection.2.bias": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.img_projection.2.weight": "model-00001-of-00003.safetensors",
    "model.embed_tokens_extend.image_embed.sub_GN": "model-00001-of-00003.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.10.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.11.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.12.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.13.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.14.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.15.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.16.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.17.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.18.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.19.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.20.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.21.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.22.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.23.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.24.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.25.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.26.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.27.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.28.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.29.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
    "model.layers.30.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
    "model.layers.30.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors",
    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.o_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.o_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.qkv_proj.base_layer.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.qkv_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.qkv_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.qkv_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
    "model.layers.31.self_attn.qkv_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors",
    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.4.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.5.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.6.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.7.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.8.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
    "model.layers.9.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors",
    "model.norm.weight": "model-00003-of-00003.safetensors"
  }
}