Hugging Face's logo

Nayantheboss
/
MNLP_M2_quantized_model

Text Generation
Transformers
Safetensors
qwen3
conversational
text-generation-inference
8-bit precision
bitsandbytes
Model card Files
xet
Community
Nayantheboss commited on
Commit
f61020c
·
verified ·
1 Parent(s): 8f08f1f

Upload Qwen3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +1 -31
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -11,36 +11,6 @@
11
  "hidden_size": 1024,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
- "layer_types": [
15
- "full_attention",
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention"
43
- ],
44
  "max_position_embeddings": 32768,
45
  "max_window_layers": 28,
46
  "model_type": "qwen3",
@@ -68,7 +38,7 @@
68
  "sliding_window": null,
69
  "tie_word_embeddings": true,
70
  "torch_dtype": "float16",
71
- "transformers_version": "4.53.0.dev0",
72
  "use_cache": true,
73
  "use_sliding_window": false,
74
  "vocab_size": 151936
 
11
  "hidden_size": 1024,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "max_position_embeddings": 32768,
15
  "max_window_layers": 28,
16
  "model_type": "qwen3",
 
38
  "sliding_window": null,
39
  "tie_word_embeddings": true,
40
  "torch_dtype": "float16",
41
+ "transformers_version": "4.52.4",
42
  "use_cache": true,
43
  "use_sliding_window": false,
44
  "vocab_size": 151936
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "bos_token_id": 151643,
3
  "eos_token_id": 151643,
4
  "max_new_tokens": 2048,
5
- "transformers_version": "4.53.0.dev0"
6
  }
 
2
  "bos_token_id": 151643,
3
  "eos_token_id": 151643,
4
  "max_new_tokens": 2048,
5
+ "transformers_version": "4.52.4"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb03aaa1cbaa7f69bad3fce4dc4c393b74dfb19956546185843ad49f1378c54
3
  size 753150052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f00eede876061d34777c6959ca830a250955f44afb8c603f9650de3617421e
3
  size 753150052