53 lines
1.2 KiB
JSON
53 lines
1.2 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "/model/Meta-Llama-3.1-8B/",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 128000,
|
||
|
|
"eos_token_id": 128001,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 14336,
|
||
|
|
"max_position_embeddings": 131072,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 4,
|
||
|
|
"checkpoint_format": "gptq",
|
||
|
|
"damp_percent": 0.01,
|
||
|
|
"desc_act": true,
|
||
|
|
"group_size": 128,
|
||
|
|
"lm_head": false,
|
||
|
|
"meta": {
|
||
|
|
"quantizer": "gptqmodel:0.9.9-dev0"
|
||
|
|
},
|
||
|
|
"model_file_base_name": null,
|
||
|
|
"model_name_or_path": null,
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"static_groups": false,
|
||
|
|
"sym": true,
|
||
|
|
"true_sequential": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 8.0,
|
||
|
|
"high_freq_factor": 4.0,
|
||
|
|
"low_freq_factor": 1.0,
|
||
|
|
"original_max_position_embeddings": 8192,
|
||
|
|
"rope_type": "llama3"
|
||
|
|
},
|
||
|
|
"rope_theta": 500000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.44.0.dev0",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 128256
|
||
|
|
}
|