| { | |
| "_name_or_path": "/home/cw/.cache/huggingface/hub/models--MediaTek-Research--Breeze-7B-32k-Instruct-v1_0/snapshots/e6512d505f287d22d7a69107250ce77500bde491", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "output_router_logits": true, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 65536, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.38.2", | |
| "use_cache": false, | |
| "vocab_size": 62464 | |
| } | |