Hugging Face's logo

project-themis
/
Themis-RM-4B

Text Classification
Transformers
Safetensors
English
qwen3
code
reward-model
multilingual
text-embeddings-inference
Model card Files
xet
 Community
iNeil77 commited on
Commit
9ddbb93
·
verified ·
1 Parent(s): 3e59afc

Upload Qwen3ForSequenceClassification

Browse files
Files changed (6) hide show
  1. config.json +40 -2
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. model.safetensors.index.json +1 -0
config.json CHANGED
@@ -4,6 +4,7 @@
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
 
7
  "eos_token_id": 151645,
8
  "head_dim": 128,
9
  "hidden_act": "silu",
@@ -16,6 +17,44 @@
16
  "label2id": {
17
  "LABEL_0": 0
18
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  "max_position_embeddings": 40960,
20
  "max_window_layers": 36,
21
  "model_type": "qwen3",
@@ -28,8 +67,7 @@
28
  "rope_theta": 1000000,
29
  "sliding_window": null,
30
  "tie_word_embeddings": true,
31
- "torch_dtype": "float32",
32
- "transformers_version": "4.51.0",
33
  "unsloth_fixed": true,
34
  "use_cache": false,
35
  "use_sliding_window": false,
 
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
+ "dtype": "float32",
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
 
17
  "label2id": {
18
  "LABEL_0": 0
19
  },
20
+ "layer_types": [
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
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention"
57
+ ],
58
  "max_position_embeddings": 40960,
59
  "max_window_layers": 36,
60
  "model_type": "qwen3",
 
67
  "rope_theta": 1000000,
68
  "sliding_window": null,
69
  "tie_word_embeddings": true,
70
+ "transformers_version": "4.57.1",
 
71
  "unsloth_fixed": true,
72
  "use_cache": false,
73
  "use_sliding_window": false,
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0aeb31c4a5b2bceda0f667f1228cda9005b1d585ae55ea1a61a91e3542ea6a9
3
  size 4990095032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8caa070b59032de9f379aae416ea0fb535480764828ee69e1eaeeb84cd64e7f7
3
  size 4990095032
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adb9c238d8ee50239297143cdeec1a7683581ddf78d1799457df90719aae4dc8
3
  size 4944309096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cddd446a8bee49504ff8d723f435dd14b14ac0a15d276f402d711edb760db82
3
  size 4944309096
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742e4a5d32ab0961f8f21ffa9185c3b9ecf88dc9904d49340012348f6d8a3953
3
  size 4996758848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac34de3fefce35533148766e7116951be7f70405c3bbffb670706032fc13f40b
3
  size 4996758848
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:425d89612f52d466501e764a109d057d73dfa3a1af5557e848e6e7f3a1814369
3
  size 1158765176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:563411a9c7dddc1565ba4eff0037970136225875a6551e1bdcd51c8849b78087
3
  size 1158765176
model.safetensors.index.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "metadata": {
 
3
  "total_size": 16089882624
4
  },
5
  "weight_map": {
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 4022470656,
4
  "total_size": 16089882624
5
  },
6
  "weight_map": {