| { |
| "architectures": [ |
| "Mistral3Model" |
| ], |
| "dtype": "bfloat16", |
| "image_token_index": 10, |
| "model_type": "mistral3", |
| "multimodal_projector_bias": false, |
| "projector_hidden_act": "gelu", |
| "quantization_config": { |
| "add_skip_keys": false, |
| "dequantize_fp32": false, |
| "dynamic_loss_threshold": null, |
| "group_size": 0, |
| "is_integer": true, |
| "is_training": false, |
| "modules_dtype_dict": {}, |
| "modules_quant_config": {}, |
| "modules_to_not_convert": [ |
| ".img_out", |
| ".proj_out", |
| ".emb_in", |
| ".final_layer", |
| "patch_embed", |
| "language_model.norm", |
| ".time_embed", |
| "multi_modal_projector", |
| ".condition_embedder", |
| ".t_embedder", |
| "wte", |
| "lm_head", |
| ".txt_out", |
| "time_text_embed", |
| ".context_embedder", |
| ".txt_in", |
| ".emb_out", |
| ".norm_out", |
| ".img_in", |
| ".vid_in", |
| ".x_embedder", |
| "patch_embedding", |
| "patch_emb", |
| ".vid_out", |
| ".y_embedder", |
| "language_model.embed_tokens.weight", |
| "language_model.layers.0.input_layernorm.weight", |
| "language_model.layers.0.post_attention_layernorm.weight", |
| "language_model.layers.1.input_layernorm.weight", |
| "language_model.layers.1.post_attention_layernorm.weight", |
| "language_model.layers.2.input_layernorm.weight", |
| "language_model.layers.2.post_attention_layernorm.weight", |
| "language_model.layers.3.input_layernorm.weight", |
| "language_model.layers.3.post_attention_layernorm.weight", |
| "language_model.layers.4.input_layernorm.weight", |
| "language_model.layers.4.post_attention_layernorm.weight", |
| "language_model.layers.5.input_layernorm.weight", |
| "language_model.layers.5.post_attention_layernorm.weight", |
| "language_model.layers.6.input_layernorm.weight", |
| "language_model.layers.6.post_attention_layernorm.weight", |
| "language_model.layers.7.input_layernorm.weight", |
| "language_model.layers.7.post_attention_layernorm.weight", |
| "language_model.layers.8.input_layernorm.weight", |
| "language_model.layers.8.post_attention_layernorm.weight", |
| "language_model.layers.9.input_layernorm.weight", |
| "language_model.layers.9.post_attention_layernorm.weight", |
| "language_model.layers.10.input_layernorm.weight", |
| "language_model.layers.10.post_attention_layernorm.weight", |
| "language_model.layers.11.input_layernorm.weight", |
| "language_model.layers.11.post_attention_layernorm.weight", |
| "language_model.layers.12.input_layernorm.weight", |
| "language_model.layers.12.post_attention_layernorm.weight", |
| "language_model.layers.13.input_layernorm.weight", |
| "language_model.layers.13.post_attention_layernorm.weight", |
| "language_model.layers.14.input_layernorm.weight", |
| "language_model.layers.14.post_attention_layernorm.weight", |
| "language_model.layers.15.input_layernorm.weight", |
| "language_model.layers.15.post_attention_layernorm.weight", |
| "language_model.layers.16.input_layernorm.weight", |
| "language_model.layers.16.post_attention_layernorm.weight", |
| "language_model.layers.17.input_layernorm.weight", |
| "language_model.layers.17.post_attention_layernorm.weight", |
| "language_model.layers.18.input_layernorm.weight", |
| "language_model.layers.18.post_attention_layernorm.weight", |
| "language_model.layers.19.input_layernorm.weight", |
| "language_model.layers.19.post_attention_layernorm.weight", |
| "language_model.layers.20.input_layernorm.weight", |
| "language_model.layers.20.post_attention_layernorm.weight", |
| "language_model.layers.21.input_layernorm.weight", |
| "language_model.layers.21.post_attention_layernorm.weight", |
| "language_model.layers.22.input_layernorm.weight", |
| "language_model.layers.22.post_attention_layernorm.weight", |
| "language_model.layers.23.input_layernorm.weight", |
| "language_model.layers.23.post_attention_layernorm.weight", |
| "language_model.layers.24.input_layernorm.weight", |
| "language_model.layers.24.post_attention_layernorm.weight", |
| "language_model.layers.25.input_layernorm.weight", |
| "language_model.layers.25.post_attention_layernorm.weight", |
| "language_model.norm.weight", |
| "multi_modal_projector.linear_1.weight", |
| "multi_modal_projector.linear_2.weight", |
| "multi_modal_projector.norm.weight", |
| "multi_modal_projector.patch_merger.merging_layer.weight", |
| "vision_tower.ln_pre.weight", |
| "vision_tower.patch_conv.weight", |
| "vision_tower.transformer.layers.0.attention_norm.weight", |
| "vision_tower.transformer.layers.0.ffn_norm.weight", |
| "vision_tower.transformer.layers.1.attention_norm.weight", |
| "vision_tower.transformer.layers.1.ffn_norm.weight", |
| "vision_tower.transformer.layers.2.attention_norm.weight", |
| "vision_tower.transformer.layers.2.ffn_norm.weight", |
| "vision_tower.transformer.layers.3.attention_norm.weight", |
| "vision_tower.transformer.layers.3.ffn_norm.weight", |
| "vision_tower.transformer.layers.4.attention_norm.weight", |
| "vision_tower.transformer.layers.4.ffn_norm.weight", |
| "vision_tower.transformer.layers.5.attention_norm.weight", |
| "vision_tower.transformer.layers.5.ffn_norm.weight", |
| "vision_tower.transformer.layers.6.attention_norm.weight", |
| "vision_tower.transformer.layers.6.ffn_norm.weight", |
| "vision_tower.transformer.layers.7.attention_norm.weight", |
| "vision_tower.transformer.layers.7.ffn_norm.weight", |
| "vision_tower.transformer.layers.8.attention_norm.weight", |
| "vision_tower.transformer.layers.8.ffn_norm.weight", |
| "vision_tower.transformer.layers.9.attention_norm.weight", |
| "vision_tower.transformer.layers.9.ffn_norm.weight", |
| "vision_tower.transformer.layers.10.attention_norm.weight", |
| "vision_tower.transformer.layers.10.ffn_norm.weight", |
| "vision_tower.transformer.layers.11.attention_norm.weight", |
| "vision_tower.transformer.layers.11.ffn_norm.weight", |
| "vision_tower.transformer.layers.12.attention_norm.weight", |
| "vision_tower.transformer.layers.12.ffn_norm.weight", |
| "vision_tower.transformer.layers.13.attention_norm.weight", |
| "vision_tower.transformer.layers.13.ffn_norm.weight", |
| "vision_tower.transformer.layers.14.attention_norm.weight", |
| "vision_tower.transformer.layers.14.ffn_norm.weight", |
| "vision_tower.transformer.layers.15.attention_norm.weight", |
| "vision_tower.transformer.layers.15.ffn_norm.weight", |
| "vision_tower.transformer.layers.16.attention_norm.weight", |
| "vision_tower.transformer.layers.16.ffn_norm.weight", |
| "vision_tower.transformer.layers.17.attention_norm.weight", |
| "vision_tower.transformer.layers.17.ffn_norm.weight", |
| "vision_tower.transformer.layers.18.attention_norm.weight", |
| "vision_tower.transformer.layers.18.ffn_norm.weight", |
| "vision_tower.transformer.layers.19.attention_norm.weight", |
| "vision_tower.transformer.layers.19.ffn_norm.weight", |
| "vision_tower.transformer.layers.20.attention_norm.weight", |
| "vision_tower.transformer.layers.20.ffn_norm.weight", |
| "vision_tower.transformer.layers.21.attention_norm.weight", |
| "vision_tower.transformer.layers.21.ffn_norm.weight", |
| "vision_tower.transformer.layers.22.attention_norm.weight", |
| "vision_tower.transformer.layers.22.ffn_norm.weight", |
| "vision_tower.transformer.layers.23.attention_norm.weight", |
| "vision_tower.transformer.layers.23.ffn_norm.weight" |
| ], |
| "modules_to_not_use_matmul": [], |
| "non_blocking": false, |
| "quant_conv": false, |
| "quant_embedding": false, |
| "quant_method": "sdnq", |
| "quantization_device": null, |
| "quantized_matmul_dtype": null, |
| "return_device": null, |
| "sdnq_version": "0.1.9", |
| "svd_rank": 32, |
| "svd_steps": 8, |
| "use_dynamic_quantization": false, |
| "use_grad_ckpt": true, |
| "use_quantized_matmul": false, |
| "use_quantized_matmul_conv": false, |
| "use_static_quantization": true, |
| "use_stochastic_rounding": false, |
| "use_svd": false, |
| "weights_dtype": "uint4" |
| }, |
| "spatial_merge_size": 2, |
| "text_config": { |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "max_position_embeddings": 262144, |
| "model_type": "mistral", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 26, |
| "num_key_value_heads": 8, |
| "pad_token_id": null, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 16.0, |
| "llama_4_scaling_beta": 0.1, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 16384, |
| "rope_theta": 1000000.0, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "vocab_size": 131072 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.8.0.dev0", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "image_size": 1540, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "model_type": "pixtral", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "patch_size": 14, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "vision_feature_layer": -1 |
| } |
|
|
