File size: 1,333 Bytes
235fe2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
{
  "_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/efficientqat_checkpoints_original/Llama-3-8b-instruct-EfficientQAT-w4g128",
  "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": 8192,
  "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": "bitblas",
    "damp_percent": 0.01,
    "desc_act": false,
    "group_size": 128,
    "lm_head": false,
    "meta": {
      "quantizer": "gptqmodel:0.9.9-dev0"
    },
    "model_file_base_name": null,
    "model_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/efficientqat_checkpoints_original/Llama-3-8b-instruct-EfficientQAT-w4g128",
    "quant_method": "gptq",
    "static_groups": false,
    "sym": false,
    "true_sequential": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "use_cache": false,
  "vocab_size": 128257
}