File size: 1,971 Bytes
fed7bd6
 
 
 
 
 
 
 
ce7ad62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9e903e
ce7ad62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fed7bd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce7ad62
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
{
  "_name_or_path": "/home/.cache/huggingface/hub/models--cmeraki--mimi_tts_hf_stage/snapshots/50932e15149e0e05f794fe80d02ab941f61fb953",
  "activation_function": "gelu",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0,
  "bos_token_id": 50256,
  "compression_config": {
    "config_groups": {
      "group_0": {
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": 1.4202334132542527,
    "ignore": [],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "dropout": 0,
  "embd_pdrop": 0,
  "eos_token_id": 50256,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_embd": 1280,
  "n_head": 20,
  "n_inner": null,
  "n_layer": 36,
  "n_positions": 1024,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.46.2",
  "use_bias": false,
  "use_cache": true,
  "vocab_size": 59968
}