config.json

{
  "architectures": [
    "QWenLMHeadModel"
  ],
  "attn_dropout_prob": 0.0,
  "bf16": false,
  "emb_dropout_prob": 0.0,
  "fp16": true,
  "fp32": false,
  "hidden_size": 8,
  "initializer_range": 0.02,
  "intermediate_size": 16,
  "kv_channels": 4,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 8192,
  "model_type": "qwen",
  "no_bias": true,
  "num_attention_heads": 2,
  "num_hidden_layers": 2,
  "rotary_emb_base": 10000,
  "rotary_pct": 1.0,
  "scale_attn_weights": true,
  "seq_length": 2048,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.35.2",
  "use_cache": true,
  "use_dynamic_ntk": true,
  "use_flash_attn": "auto",
  "use_logn_attn": true,
  "visual": {
    "heads": 2,
    "image_size": 448,
    "image_start_id": 151857,
    "layers": 2,
    "mlp_ratio": 1.0,
    "output_dim": 8,
    "patch_size": 14,
    "width": 8
  },
  "vocab_size": 151936
}