File size: 4,515 Bytes
723428d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
{
  "_name_or_path": "/slot/sandbox/j/_tmp/data56i42hhp",
  "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": {
    "in_group_size": 8,
    "linear_weights_not_to_quantize": [
      "model.layers.0.input_layernorm.weight",
      "model.layers.0.post_attention_layernorm.weight",
      "model.layers.1.input_layernorm.weight",
      "model.layers.1.post_attention_layernorm.weight",
      "model.layers.2.input_layernorm.weight",
      "model.layers.2.post_attention_layernorm.weight",
      "model.layers.3.input_layernorm.weight",
      "model.layers.3.post_attention_layernorm.weight",
      "model.layers.4.input_layernorm.weight",
      "model.layers.4.post_attention_layernorm.weight",
      "model.layers.5.input_layernorm.weight",
      "model.layers.5.post_attention_layernorm.weight",
      "model.layers.6.input_layernorm.weight",
      "model.layers.6.post_attention_layernorm.weight",
      "model.layers.7.input_layernorm.weight",
      "model.layers.7.post_attention_layernorm.weight",
      "model.layers.8.input_layernorm.weight",
      "model.layers.8.post_attention_layernorm.weight",
      "model.layers.9.input_layernorm.weight",
      "model.layers.9.post_attention_layernorm.weight",
      "model.layers.10.input_layernorm.weight",
      "model.layers.10.post_attention_layernorm.weight",
      "model.layers.11.input_layernorm.weight",
      "model.layers.11.post_attention_layernorm.weight",
      "model.layers.12.input_layernorm.weight",
      "model.layers.12.post_attention_layernorm.weight",
      "model.layers.13.input_layernorm.weight",
      "model.layers.13.post_attention_layernorm.weight",
      "model.layers.14.input_layernorm.weight",
      "model.layers.14.post_attention_layernorm.weight",
      "model.layers.15.input_layernorm.weight",
      "model.layers.15.post_attention_layernorm.weight",
      "model.layers.16.input_layernorm.weight",
      "model.layers.16.post_attention_layernorm.weight",
      "model.layers.17.input_layernorm.weight",
      "model.layers.17.post_attention_layernorm.weight",
      "model.layers.18.input_layernorm.weight",
      "model.layers.18.post_attention_layernorm.weight",
      "model.layers.19.input_layernorm.weight",
      "model.layers.19.post_attention_layernorm.weight",
      "model.layers.20.input_layernorm.weight",
      "model.layers.20.post_attention_layernorm.weight",
      "model.layers.21.input_layernorm.weight",
      "model.layers.21.post_attention_layernorm.weight",
      "model.layers.22.input_layernorm.weight",
      "model.layers.22.post_attention_layernorm.weight",
      "model.layers.23.input_layernorm.weight",
      "model.layers.23.post_attention_layernorm.weight",
      "model.layers.24.input_layernorm.weight",
      "model.layers.24.post_attention_layernorm.weight",
      "model.layers.25.input_layernorm.weight",
      "model.layers.25.post_attention_layernorm.weight",
      "model.layers.26.input_layernorm.weight",
      "model.layers.26.post_attention_layernorm.weight",
      "model.layers.27.input_layernorm.weight",
      "model.layers.27.post_attention_layernorm.weight",
      "model.layers.28.input_layernorm.weight",
      "model.layers.28.post_attention_layernorm.weight",
      "model.layers.29.input_layernorm.weight",
      "model.layers.29.post_attention_layernorm.weight",
      "model.layers.30.input_layernorm.weight",
      "model.layers.30.post_attention_layernorm.weight",
      "model.layers.31.input_layernorm.weight",
      "model.layers.31.post_attention_layernorm.weight",
      "model.embed_tokens.weight",
      "model.norm.weight",
      "lm_head.weight"
    ],
    "nbits_per_codebook": 16,
    "num_codebooks": 1,
    "out_group_size": 1,
    "quant_method": "aqlm"
  },
  "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": "float16",
  "transformers_version": "4.44.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
}