cmeraki commited on
Commit
ce7ad62
·
verified ·
1 Parent(s): 6be5c9e

Upload model

Browse files
Files changed (2) hide show
  1. config.json +41 -1
  2. model.safetensors +2 -2
config.json CHANGED
@@ -6,6 +6,46 @@
6
  ],
7
  "attn_pdrop": 0,
8
  "bos_token_id": 50256,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "dropout": 0,
10
  "embd_pdrop": 0,
11
  "eos_token_id": 50256,
@@ -31,4 +71,4 @@
31
  "use_bias": false,
32
  "use_cache": true,
33
  "vocab_size": 59968
34
- }
 
6
  ],
7
  "attn_pdrop": 0,
8
  "bos_token_id": 50256,
9
+ "compression_config": {
10
+ "config_groups": {
11
+ "group_0": {
12
+ "input_activations": {
13
+ "actorder": null,
14
+ "block_structure": null,
15
+ "dynamic": false,
16
+ "group_size": null,
17
+ "num_bits": 8,
18
+ "observer": "minmax",
19
+ "observer_kwargs": {},
20
+ "strategy": "tensor",
21
+ "symmetric": true,
22
+ "type": "float"
23
+ },
24
+ "output_activations": null,
25
+ "targets": [
26
+ "Conv1D"
27
+ ],
28
+ "weights": {
29
+ "actorder": null,
30
+ "block_structure": null,
31
+ "dynamic": false,
32
+ "group_size": null,
33
+ "num_bits": 8,
34
+ "observer": "minmax",
35
+ "observer_kwargs": {},
36
+ "strategy": "tensor",
37
+ "symmetric": true,
38
+ "type": "float"
39
+ }
40
+ }
41
+ },
42
+ "format": "float-quantized",
43
+ "global_compression_ratio": 1.4202334132542527,
44
+ "ignore": [],
45
+ "kv_cache_scheme": null,
46
+ "quant_method": "compressed-tensors",
47
+ "quantization_status": "compressed"
48
+ },
49
  "dropout": 0,
50
  "embd_pdrop": 0,
51
  "eos_token_id": 50256,
 
71
  "use_bias": false,
72
  "use_cache": true,
73
  "vocab_size": 59968
74
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9ee5ac012483ce97af9b7ea8416cb5d8e95e40b8a17bf8bf9b5d708e17f93af
3
- size 3145886248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259178da0238583d14e68456758f4e9b35f9a890f45f1d9f849776ef6746c448
3
+ size 1329588320