Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/path/to/your/VITA_ckpt",
+  "architectures": [
+    "VITAMixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_audio_encoder": true,
+  "freeze_audio_encoder_adapter": false,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "square",
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mm_audio_encoder": "/path/to/your/audio-encoder-2wh_zh_en_audioset_Mixtral-8x7B_New-base-tunning",
+  "mm_hidden_size": 4096,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_tower": "/path/to/your/InternViT-300M-448px",
+  "model_type": "vita-mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 9100,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "tune_mm_mlp_adapter": true,
+  "unfreeze_vision_tower": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_s2": false,
+  "vocab_size": 51760
+}