File size: 1,454 Bytes
5011fa2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
48
49
50
51
52
53
54
55
56
{
  "_name_or_path": "facebook/opt-125m",
  "_remove_final_layer_norm": false,
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "OPTForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "do_layer_norm_before": true,
  "dropout": 0.1,
  "enable_bias": true,
  "eos_token_id": 2,
  "ffn_dim": 3072,
  "hidden_size": 768,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "prefix": "</s>",
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": "model.decoder.layers",
    "damp_percent": 0.01,
    "dataset": [
      "auto-gptq is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm."
    ],
    "desc_act": false,
    "group_size": 128,
    "model_seqlen": 2048,
    "module_name_preceding_first_block": [
      "model.decoder.embed_tokens",
      "model.decoder.embed_positions",
      "model.decoder.final_layer_norm"
    ],
    "pack_sequentially": false,
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": true
  },
  "torch_dtype": "float16",
  "transformers_version": "4.32.0.dev0",
  "use_cache": true,
  "vocab_size": 50272,
  "word_embed_proj_dim": 768
}