Hugging Face's logo

project-themis
/
Themis-RM-1.7B

Text Classification
Transformers
Safetensors
English
qwen3
code
reward-model
multilingual
text-embeddings-inference
Model card Files
xet
 Community
iNeil77 commited on
Commit
0aace4e
·
verified ·
1 Parent(s): aca6b22

Upload Qwen3ForSequenceClassification

Browse files
Files changed (4) hide show
  1. config.json +32 -2
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. 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 +17,36 @@
16
  "label2id": {
17
  "LABEL_0": 0
18
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  "max_position_embeddings": 40960,
20
  "max_window_layers": 28,
21
  "model_type": "qwen3",
@@ -28,8 +59,7 @@
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
+ ],
50
  "max_position_embeddings": 40960,
51
  "max_window_layers": 28,
52
  "model_type": "qwen3",
 
59
  "rope_theta": 1000000,
60
  "sliding_window": null,
61
  "tie_word_embeddings": true,
62
+ "transformers_version": "4.57.1",
 
63
  "unsloth_fixed": true,
64
  "use_cache": false,
65
  "use_sliding_window": false,
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcd3cbf144ef28655be0f323902785d7e6bdf7a0deff0fb4d2eb56ac5ba5c3e0
3
  size 4969539560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b78c3dff91649f057eb7dbf9dd9894f777e2c26dcde1797d4dd32e9c8562b02
3
  size 4969539560
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48fdb07bce7e46b9063f14bc5d5dcdcc976a65be71cffd1217886f6f16c094bc
3
  size 1912803968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e463945705033814fa7221fbc37fc7d99f6a44227a5fccef52a136101e98f7e
3
  size 1912803968
model.safetensors.index.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "metadata": {
 
3
  "total_size": 6882308096
4
  },
5
  "weight_map": {
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 1720577024,
4
  "total_size": 6882308096
5
  },
6
  "weight_map": {