| { |
| "architectures": [ |
| "Mistral3ForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "image_token_index": 10, |
| "model_type": "mistral3", |
| "multimodal_projector_bias": false, |
| "projector_hidden_act": "gelu", |
| "spatial_merge_size": 2, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "first_k_dense_replace": 0, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 8, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "kv_lora_rank": 256, |
| "max_position_embeddings": 1048576, |
| "mlp_bias": false, |
| "model_type": "mistral4", |
| "moe_intermediate_size": 32, |
| "n_group": 1, |
| "n_routed_experts": 128, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 32, |
| "pad_token_id": 11, |
| "pretraining_tp": 1, |
| "q_lora_rank": 32, |
| "qk_head_dim": 128, |
| "qk_nope_head_dim": 64, |
| "qk_rope_head_dim": 64, |
| "rms_norm_eps": 1e-06, |
| "rope_interleave": true, |
| "rope_parameters": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 128.0, |
| "llama_4_scaling_beta": 0.1, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 8192, |
| "partial_rotary_factor": 0.5, |
| "rope_theta": 10000.0, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "routed_scaling_factor": 1.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "topk_group": 1, |
| "use_cache": true, |
| "v_head_dim": 128, |
| "vocab_size": 131072 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.5.0", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "head_dim": 32, |
| "hidden_act": "silu", |
| "hidden_size": 64, |
| "image_size": 1540, |
| "initializer_range": 0.02, |
| "intermediate_size": 64, |
| "model_type": "pixtral", |
| "num_attention_heads": 2, |
| "num_channels": 3, |
| "num_hidden_layers": 2, |
| "patch_size": 14, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "vision_feature_layer": -1 |
| } |
|
|