| { |
| "architectures": [ |
| "Mistral3ForSequenceClassification" |
| ], |
| "auto_map": { |
| "AutoModelForSequenceClassification": "model.Mistral3ForSequenceClassification" |
| }, |
| "chunk_size_feed_forward": 0, |
| "dtype": "bfloat16", |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "image_token_index": 10, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "model_type": "mistral3", |
| "multimodal_projector_bias": false, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pooling": "avg", |
| "problem_type": null, |
| "projector_hidden_act": "gelu", |
| "return_dict": true, |
| "rope_theta": 1000000.0, |
| "spatial_merge_size": 2, |
| "text_config": { |
| "_name_or_path": "", |
| "architectures": [ |
| "Ministral3ForSequenceClassification" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "chunk_size_feed_forward": 0, |
| "dtype": "bfloat16", |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "is_causal": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "max_position_embeddings": 262144, |
| "model_type": "ministral3", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 34, |
| "num_key_value_heads": 8, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pad_token_id": 11, |
| "pooling": "avg", |
| "problem_type": null, |
| "return_dict": true, |
| "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", |
| "apply_yarn_scaling": false |
| }, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "use_cache": false, |
| "vocab_size": 131072, |
| "llama_4_scaling": { |
| "beta": 0.1, |
| "original_max_position_embeddings": 16384 |
| } |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.12.1", |
| "use_cache": false, |
| "vision_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "attention_dropout": 0.0, |
| "chunk_size_feed_forward": 0, |
| "dtype": "bfloat16", |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": 1540, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "model_type": "pixtral", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_size": 14, |
| "problem_type": null, |
| "return_dict": true, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "vision_feature_layer": -1, |
| "is_causal": false, |
| "nemotron_mlx": { |
| "kind": "rerank", |
| "source": "Nemotron-3.5-Rerank-8B-BF16", |
| "revision": "f88f8d9104726747791283ab156d2fcdb29e90a7", |
| "bits": 8, |
| "text_only": false, |
| "kept_full_precision": [ |
| "norms", |
| "vision encoder and projector (bf16)", |
| "score head (float32)" |
| ] |
| }, |
| "quantization": { |
| "group_size": 64, |
| "bits": 8, |
| "mode": "affine" |
| } |
| } |
