Hugging Face's logo

Splashdude
/
reasoning-chat-model-7b

Safetensors
qwen2
Model card Files
xet
 Community
Splashdude commited on
Commit
bf974b2
·
verified ·
1 Parent(s): bd9a0fc

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +61 -61
  2. model.safetensors +2 -2
  3. tokenizer.json +2 -2
config.json CHANGED
@@ -1,61 +1,61 @@
1
- {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 3584,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 18944,
13
- "layer_types": [
14
- "full_attention",
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
- ],
43
- "max_position_embeddings": 32768,
44
- "max_window_layers": 28,
45
- "model_type": "qwen2",
46
- "num_attention_heads": 28,
47
- "num_hidden_layers": 28,
48
- "num_key_value_heads": 4,
49
- "pad_token_id": null,
50
- "rms_norm_eps": 1e-06,
51
- "rope_parameters": {
52
- "rope_theta": 1000000.0,
53
- "rope_type": "default"
54
- },
55
- "sliding_window": null,
56
- "tie_word_embeddings": false,
57
- "transformers_version": "5.0.0",
58
- "use_cache": true,
59
- "use_sliding_window": false,
60
- "vocab_size": 152064
61
- }
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
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
+ ],
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.0.0",
58
+ "use_cache": true,
59
+ "use_sliding_window": false,
60
+ "vocab_size": 152064
61
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f46d1b7a68e31c6052c086f65521208638d9ab22716e6a5a8c567a3ee25eade
3
- size 5547254438
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf92a7b5b68b63f06702489096292171319f2e998e41c1efcb5ba3cc0fecd920
3
+ size 8705983080
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
3
- size 11421991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892