{ "transformers_version": "5.5.0", "architectures": [ "MistralForCausalLM" ], "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 32000, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "max_position_embeddings": 32768, "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "pad_token_id": null, "bos_token_id": 1, "eos_token_id": 2, "tie_word_embeddings": false, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "sliding_window": 4096, "attention_dropout": 0.0, "_name_or_path": "mistralai/Mistral-7B-v0.1", "model_type": "mistral", "output_attentions": false, "quantization": { "group_size": 64, "bits": 4 } }