Hugging Face's logo

PatrickG1014
/
intercode_sql-1.5b-step

Safetensors
qwen2
Model card Files
xet
Community
PatrickG1014 commited on
Commit
57c05a2
·
verified ·
1 Parent(s): 84dcada

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +32 -2
  2. generation_config.json +1 -1
  3. model.safetensors +2 -2
  4. tokenizer.json +1 -1
config.json CHANGED
@@ -9,6 +9,36 @@
9
  "hidden_size": 1536,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 8960,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "max_position_embeddings": 32768,
13
  "max_window_layers": 21,
14
  "model_type": "qwen2",
@@ -18,10 +48,10 @@
18
  "rms_norm_eps": 1e-06,
19
  "rope_scaling": null,
20
  "rope_theta": 1000000.0,
21
- "sliding_window": 32768,
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
- "transformers_version": "4.52.4",
25
  "use_cache": false,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
 
9
  "hidden_size": 1536,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 8960,
12
+ "layer_types": [
13
+ "full_attention",
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
+ ],
42
  "max_position_embeddings": 32768,
43
  "max_window_layers": 21,
44
  "model_type": "qwen2",
 
48
  "rms_norm_eps": 1e-06,
49
  "rope_scaling": null,
50
  "rope_theta": 1000000.0,
51
+ "sliding_window": null,
52
  "tie_word_embeddings": true,
53
  "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.54.1",
55
  "use_cache": false,
56
  "use_sliding_window": false,
57
  "vocab_size": 151936
generation_config.json CHANGED
@@ -10,5 +10,5 @@
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
- "transformers_version": "4.52.4"
14
  }
 
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
+ "transformers_version": "4.54.1"
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:309167af39533832e3fba176b406821e8d6ad887e2f9fe6caf8eb1b4ba8b49ac
3
- size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3528446684b7c0e48733020b40ac0452f53a884185ad9c087b4a8d311dcbb26
3
+ size 3554214752
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33624f49f1034c4f5d92e3ec47ccdf80ccd02caf1eb1d769872ba7fb1e5be112
3
  size 11421995
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
3
  size 11421995