|
{ |
|
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--NousResearch--Hermes-2-Pro-Llama-3-8B/snapshots/8722c0bdf7845a2c4e551ea18ace8139abbaa075", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 128000, |
|
"eos_token_id": 128003, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 8192, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"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-05, |
|
"rope_scaling": null, |
|
"rope_theta": 500000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.38.2", |
|
"use_cache": false, |
|
"vocab_size": 128288 |
|
} |
|
|