Nahush-27 commited on
Commit
a374228
·
verified ·
1 Parent(s): 3ae0570

v7 ck1100: GRPO from base_fmt, step 1100/4000 (27.5%), eval-v2 16k: 57.2% MMLU-Pro / 27.8% SuperGPQA / 42.5% overall

Browse files
Files changed (3) hide show
  1. config.json +38 -5
  2. generation_config.json +12 -12
  3. model.safetensors +3 -0
config.json CHANGED
@@ -5,26 +5,59 @@
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
 
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
11
  "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 6144,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "max_position_embeddings": 40960,
15
  "max_window_layers": 28,
16
  "model_type": "qwen3",
17
  "num_attention_heads": 16,
18
  "num_hidden_layers": 28,
19
  "num_key_value_heads": 8,
 
20
  "rms_norm_eps": 1e-06,
21
- "rope_scaling": null,
22
- "rope_theta": 1000000,
 
 
23
  "sliding_window": null,
24
  "tie_word_embeddings": true,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.51.0",
27
  "use_cache": true,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
- }
 
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
  "eos_token_id": 151645,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 2048,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 6144,
15
+ "layer_types": [
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
+ "full_attention"
44
+ ],
45
  "max_position_embeddings": 40960,
46
  "max_window_layers": 28,
47
  "model_type": "qwen3",
48
  "num_attention_heads": 16,
49
  "num_hidden_layers": 28,
50
  "num_key_value_heads": 8,
51
+ "pad_token_id": null,
52
  "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
  "sliding_window": null,
58
  "tie_word_embeddings": true,
59
+ "transformers_version": "5.7.0",
 
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
  "vocab_size": 151936
63
+ }
generation_config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.51.0"
13
- }
 
1
  {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.7.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c64bae2caebb14bf67eee6180003cabc59d295fbce577801388b6f5c59ce033
3
+ size 3441185608