Hugging Face's logo

project-themis
/
Themis-RM-8B

Text Classification
Transformers
Safetensors
English
qwen3
code
reward-model
multilingual
text-embeddings-inference
Model card Files
xet
 Community
iNeil77 commited on
Commit
457fe3a
·
verified ·
1 Parent(s): 46815ed

Upload Qwen3ForSequenceClassification

Browse files
Files changed (9) hide show
  1. config.json +40 -2
  2. model-00001-of-00007.safetensors +1 -1
  3. model-00002-of-00007.safetensors +1 -1
  4. model-00003-of-00007.safetensors +1 -1
  5. model-00004-of-00007.safetensors +1 -1
  6. model-00005-of-00007.safetensors +1 -1
  7. model-00006-of-00007.safetensors +1 -1
  8. model-00007-of-00007.safetensors +1 -1
  9. 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": false,
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": false,
70
+ "transformers_version": "4.57.6",
 
71
  "unsloth_fixed": true,
72
  "use_cache": false,
73
  "use_sliding_window": false,
model-00001-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:360a29529b80b5d5f9dc2840f273a47471798ea92e087278212818186f5da357
3
  size 4972454376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af23a8459ffe849bd48b1b4dd83425411e2a9d26e36918a617dff4351d2b839d
3
  size 4972454376
model-00002-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b976945d6f30412d4d0c68b3c1916a10c5c40060c2fbc0a6db49b2df2cbed75e
3
  size 4832048608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d3250096656adb2baf16289995757773c871e6922c1e73c2c3bf8a54285e5e
3
  size 4832048608
model-00003-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8dccfd2c568731480ca9e9d5a27edab46128d46a08ea96a81b0eeac6ee1c4f7
3
  size 4832048656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7e46f77f542616c0c872e54bc658f7a6788795630923cb369c8329116efa8f
3
  size 4832048656
model-00004-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e900230a4be726d86b6bd2c390ad0d703b0ee7e89f51f7266ec8420037c54e9
3
  size 4999855528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:410daab694ca5bfcca8e69a5749bd561554e2e472d9dc0cf1c82cf622b59a2b8
3
  size 4999855528
model-00005-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65a7086141d0c4404fb9340c2323df92ab5af20d23b24672b32d69fcaf55f2b3
3
  size 4832048672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b1d970edabb99cb3583e919dbd0b7bd96b15b089c6809df454f8728584a405
3
  size 4832048672
model-00006-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:402cb7cacc214de32b5d8af354d67f2af62a8bdd639fab2932dde4f7442c8ded
3
  size 4832048672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3b4e06edcd3c0649365ac2d7c870e99a13490795315b4ad2abb9249fb58168
3
  size 4832048672
model-00007-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa74d08972e425a76955a1781a6fdc19309d1f99d57dddc1ab2f3b6ead8a082e
3
  size 973179640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42c545a4ebe121ddd4dda89c5e3fabb91f817bc631c150db836282b9462a8b8
3
  size 973179640
model.safetensors.index.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "metadata": {
 
3
  "total_size": 30273638400
4
  },
5
  "weight_map": {
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 7568409600,
4
  "total_size": 30273638400
5
  },
6
  "weight_map": {