File size: 1,399 Bytes
37b17ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "QuantizedLinear": {
    "is_quant_weight": false,
    "outlier_ids": {},
    "replace": false,
    "training_mode": "train_full"
  },
  "_name_or_path": "/home/exp_results/quik/llama7b_sym8bit_quik_scales_after_admm_sparsity_0@50",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "clip_softmax_eta": 1,
  "clip_softmax_gamma": 0,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "symmetric_quantizer": {
    "add": false,
    "layer_bit": {},
    "learnable_scale": false
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.0.dev0",
  "use_cache": true,
  "vocab_size": 32000,
  "weight_quant_bitnoise": {
    "add": false,
    "compute_scale": false,
    "layer_bit": {},
    "learnable_scale": false,
    "noise_type": "normal",
    "predict": false
  },
  "weight_quant_noise": {
    "add": false,
    "block_size": null,
    "compute_scale": false,
    "fp_cols_num": null,
    "layer_bit": {},
    "predict": false
  }
}