{ | |
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsoylmdk26r5nqif4d", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bias": false, | |
"bos_token_id": 32013, | |
"eos_token_id": 32021, | |
"hidden_act": "silu", | |
"hidden_size": 4096, | |
"initializer_range": 0.02, | |
"intermediate_size": 11008, | |
"max_position_embeddings": 16384, | |
"mlp_bias": false, | |
"model_type": "llama", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 32, | |
"num_key_value_heads": 32, | |
"pad_token_id": 32014, | |
"pretraining_tp": 1, | |
"quantization_config": { | |
"bits": 4, | |
"group_size": 128, | |
"modules_to_not_convert": null, | |
"quant_method": "awq", | |
"version": "gemm", | |
"zero_point": true | |
}, | |
"rms_norm_eps": 1e-06, | |
"rope_scaling": { | |
"factor": 4.0, | |
"type": "linear" | |
}, | |
"rope_theta": 100000, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.41.2", | |
"use_cache": false, | |
"vocab_size": 32256 | |
} | |