Hugging Face's logo

nareshmlx
/
code-reviewer-opencv-16k

Text Generation
Transformers
Safetensors
English
qwen2
text-generation-inference
unsloth
conversational
Model card Files
xet
Community
nareshmlx commited on
Commit
dc4d070
·
verified ·
1 Parent(s): 5a5ac0c

Fine-tuned OpenCV code reviewer (Trained with Unsloth)

Browse files
Files changed (6) hide show
  1. README.md +2 -0
  2. config.json +72 -60
  3. generation_config.json +15 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +0 -0
README.md CHANGED
@@ -5,6 +5,8 @@ tags:
5
  - transformers
6
  - unsloth
7
  - qwen2
 
 
8
  license: apache-2.0
9
  language:
10
  - en
 
5
  - transformers
6
  - unsloth
7
  - qwen2
8
+ - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json CHANGED
@@ -1,61 +1,73 @@
1
  {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "eos_token_id": 151645,
8
- "hidden_act": "silu",
9
- "hidden_size": 3584,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 18944,
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": 28,
44
- "model_type": "qwen2",
45
- "num_attention_heads": 28,
46
- "num_hidden_layers": 28,
47
- "num_key_value_heads": 4,
48
- "pad_token_id": 151665,
49
- "rms_norm_eps": 1e-06,
50
- "rope_scaling": null,
51
- "rope_theta": 1000000.0,
52
- "sliding_window": null,
53
- "tie_word_embeddings": false,
54
- "torch_dtype": "bfloat16",
55
- "transformers_version": "4.55.4",
56
- "unsloth_fixed": true,
57
- "unsloth_version": "2025.10.1",
58
- "use_cache": true,
59
- "use_sliding_window": false,
60
- "vocab_size": 152064
61
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
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": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "pad_token_id": 151665,
49
+ "quantization_config": {
50
+ "bnb_4bit_compute_dtype": "bfloat16",
51
+ "bnb_4bit_quant_type": "nf4",
52
+ "bnb_4bit_use_double_quant": true,
53
+ "llm_int8_enable_fp32_cpu_offload": false,
54
+ "llm_int8_has_fp16_weight": false,
55
+ "llm_int8_skip_modules": null,
56
+ "llm_int8_threshold": 6.0,
57
+ "load_in_4bit": true,
58
+ "load_in_8bit": false,
59
+ "quant_method": "bitsandbytes"
60
+ },
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_scaling": null,
63
+ "rope_theta": 1000000.0,
64
+ "sliding_window": null,
65
+ "tie_word_embeddings": false,
66
+ "torch_dtype": "bfloat16",
67
+ "transformers_version": "4.55.4",
68
+ "unsloth_fixed": true,
69
+ "unsloth_version": "2025.10.5",
70
+ "use_cache": true,
71
+ "use_sliding_window": false,
72
+ "vocab_size": 152064
73
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 32768,
9
+ "pad_token_id": 151665,
10
+ "repetition_penalty": 1.1,
11
+ "temperature": 0.7,
12
+ "top_k": 20,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.55.4"
15
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bc61d11d0002c3026e25c0eee943759148af679307890c2a35786775f60bf6
3
+ size 4457259593
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2
3
+ size 1089994880
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff