larryvrh commited on
Commit
d7168a4
·
verified ·
1 Parent(s): 1e765fd

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +5 -46
  2. generation_config.json +1 -1
  3. model.safetensors +3 -0
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "model/Qwen_Qwen2.5-7B-Instruct/",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
  "eos_token_id": 151645,
 
9
  "hidden_act": "silu",
10
  "hidden_size": 3584,
11
  "initializer_range": 0.02,
@@ -16,56 +17,14 @@
16
  "num_attention_heads": 28,
17
  "num_hidden_layers": 28,
18
  "num_key_value_heads": 4,
19
- "quantization_config": {
20
- "config_groups": {
21
- "group_0": {
22
- "input_activations": {
23
- "actorder": null,
24
- "block_structure": null,
25
- "dynamic": true,
26
- "group_size": null,
27
- "num_bits": 8,
28
- "observer": null,
29
- "observer_kwargs": {},
30
- "strategy": "token",
31
- "symmetric": true,
32
- "type": "float"
33
- },
34
- "output_activations": null,
35
- "targets": [
36
- "Linear"
37
- ],
38
- "weights": {
39
- "actorder": null,
40
- "block_structure": null,
41
- "dynamic": false,
42
- "group_size": null,
43
- "num_bits": 8,
44
- "observer": "minmax",
45
- "observer_kwargs": {},
46
- "strategy": "channel",
47
- "symmetric": true,
48
- "type": "float"
49
- }
50
- }
51
- },
52
- "format": "float-quantized",
53
- "global_compression_ratio": 1.5268082955288436,
54
- "ignore": [
55
- "lm_head"
56
- ],
57
- "kv_cache_scheme": null,
58
- "quant_method": "compressed-tensors",
59
- "quantization_status": "compressed"
60
- },
61
  "rms_norm_eps": 1e-06,
62
- "rope_scaling": null,
63
  "rope_theta": 1000000.0,
64
  "sliding_window": null,
65
  "tie_word_embeddings": false,
66
  "torch_dtype": "bfloat16",
67
- "transformers_version": "4.48.3",
68
  "use_cache": true,
 
69
  "use_sliding_window": false,
70
  "vocab_size": 152064
71
- }
 
1
  {
2
+ "_name_or_path": "Qwen2.5-7B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
  "eos_token_id": 151645,
9
+ "fmo_version": "0.2",
10
  "hidden_act": "silu",
11
  "hidden_size": 3584,
12
  "initializer_range": 0.02,
 
17
  "num_attention_heads": 28,
18
  "num_hidden_layers": 28,
19
  "num_key_value_heads": 4,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  "rms_norm_eps": 1e-06,
 
21
  "rope_theta": 1000000.0,
22
  "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.43.1",
26
  "use_cache": true,
27
+ "use_fp8_e4m3": true,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
30
+ }
generation_config.json CHANGED
@@ -10,5 +10,5 @@
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
- "transformers_version": "4.48.3"
14
  }
 
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
+ "transformers_version": "4.43.1"
14
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb237d2f11f2f4b841392760930e31c17453165e21e4a7fb9725a59a9a00379
3
+ size 8706022496