{ | |
"_name_or_path": "/workspace/process/nousresearch_yarn-mistral-7b-64k/source", | |
"architectures": [ | |
"MistralForCausalLM" | |
], | |
"auto_map": { | |
"AutoConfig": "configuration_mistral.MistralConfig", | |
"AutoModelForCausalLM": "modeling_mistral_yarn.MistralForCausalLM" | |
}, | |
"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, | |
"pad_token_id": 0, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": { | |
"factor": 8.0, | |
"finetuned": true, | |
"original_max_position_embeddings": 8192, | |
"type": "yarn" | |
}, | |
"rope_theta": 10000.0, | |
"sliding_window": 65536, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.35.0", | |
"use_cache": true, | |
"vocab_size": 32000, | |
"quantization_config": { | |
"quant_method": "awq", | |
"zero_point": true, | |
"group_size": 128, | |
"bits": 4, | |
"version": "gemm" | |
} | |
} |