| { | |
| "_name_or_path": "/slot/sandbox/j/_tmp/datahsc_3r4_", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 1024000, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "quantization_config": { | |
| "in_group_size": 8, | |
| "linear_weights_not_to_quantize": [ | |
| "model.layers.0.input_layernorm.weight", | |
| "model.layers.0.post_attention_layernorm.weight", | |
| "model.layers.1.input_layernorm.weight", | |
| "model.layers.1.post_attention_layernorm.weight", | |
| "model.layers.2.input_layernorm.weight", | |
| "model.layers.2.post_attention_layernorm.weight", | |
| "model.layers.3.input_layernorm.weight", | |
| "model.layers.3.post_attention_layernorm.weight", | |
| "model.layers.4.input_layernorm.weight", | |
| "model.layers.4.post_attention_layernorm.weight", | |
| "model.layers.5.input_layernorm.weight", | |
| "model.layers.5.post_attention_layernorm.weight", | |
| "model.layers.6.input_layernorm.weight", | |
| "model.layers.6.post_attention_layernorm.weight", | |
| "model.layers.7.input_layernorm.weight", | |
| "model.layers.7.post_attention_layernorm.weight", | |
| "model.layers.8.input_layernorm.weight", | |
| "model.layers.8.post_attention_layernorm.weight", | |
| "model.layers.9.input_layernorm.weight", | |
| "model.layers.9.post_attention_layernorm.weight", | |
| "model.layers.10.input_layernorm.weight", | |
| "model.layers.10.post_attention_layernorm.weight", | |
| "model.layers.11.input_layernorm.weight", | |
| "model.layers.11.post_attention_layernorm.weight", | |
| "model.layers.12.input_layernorm.weight", | |
| "model.layers.12.post_attention_layernorm.weight", | |
| "model.layers.13.input_layernorm.weight", | |
| "model.layers.13.post_attention_layernorm.weight", | |
| "model.layers.14.input_layernorm.weight", | |
| "model.layers.14.post_attention_layernorm.weight", | |
| "model.layers.15.input_layernorm.weight", | |
| "model.layers.15.post_attention_layernorm.weight", | |
| "model.layers.16.input_layernorm.weight", | |
| "model.layers.16.post_attention_layernorm.weight", | |
| "model.layers.17.input_layernorm.weight", | |
| "model.layers.17.post_attention_layernorm.weight", | |
| "model.layers.18.input_layernorm.weight", | |
| "model.layers.18.post_attention_layernorm.weight", | |
| "model.layers.19.input_layernorm.weight", | |
| "model.layers.19.post_attention_layernorm.weight", | |
| "model.layers.20.input_layernorm.weight", | |
| "model.layers.20.post_attention_layernorm.weight", | |
| "model.layers.21.input_layernorm.weight", | |
| "model.layers.21.post_attention_layernorm.weight", | |
| "model.layers.22.input_layernorm.weight", | |
| "model.layers.22.post_attention_layernorm.weight", | |
| "model.layers.23.input_layernorm.weight", | |
| "model.layers.23.post_attention_layernorm.weight", | |
| "model.layers.24.input_layernorm.weight", | |
| "model.layers.24.post_attention_layernorm.weight", | |
| "model.layers.25.input_layernorm.weight", | |
| "model.layers.25.post_attention_layernorm.weight", | |
| "model.layers.26.input_layernorm.weight", | |
| "model.layers.26.post_attention_layernorm.weight", | |
| "model.layers.27.input_layernorm.weight", | |
| "model.layers.27.post_attention_layernorm.weight", | |
| "model.layers.28.input_layernorm.weight", | |
| "model.layers.28.post_attention_layernorm.weight", | |
| "model.layers.29.input_layernorm.weight", | |
| "model.layers.29.post_attention_layernorm.weight", | |
| "model.layers.30.input_layernorm.weight", | |
| "model.layers.30.post_attention_layernorm.weight", | |
| "model.layers.31.input_layernorm.weight", | |
| "model.layers.31.post_attention_layernorm.weight", | |
| "model.layers.32.input_layernorm.weight", | |
| "model.layers.32.post_attention_layernorm.weight", | |
| "model.layers.33.input_layernorm.weight", | |
| "model.layers.33.post_attention_layernorm.weight", | |
| "model.layers.34.input_layernorm.weight", | |
| "model.layers.34.post_attention_layernorm.weight", | |
| "model.layers.35.input_layernorm.weight", | |
| "model.layers.35.post_attention_layernorm.weight", | |
| "model.layers.36.input_layernorm.weight", | |
| "model.layers.36.post_attention_layernorm.weight", | |
| "model.layers.37.input_layernorm.weight", | |
| "model.layers.37.post_attention_layernorm.weight", | |
| "model.layers.38.input_layernorm.weight", | |
| "model.layers.38.post_attention_layernorm.weight", | |
| "model.layers.39.input_layernorm.weight", | |
| "model.layers.39.post_attention_layernorm.weight", | |
| "model.embed_tokens.weight", | |
| "model.norm.weight", | |
| "lm_head.weight" | |
| ], | |
| "nbits_per_codebook": 16, | |
| "num_codebooks": 1, | |
| "out_group_size": 1, | |
| "quant_method": "aqlm" | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.44.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| } | |