Hugging Face's logo

anirvankrishna
/
model_sft_lora_fused

Text Generation
Transformers
Safetensors
qwen2
text-generation-inference
Model card Files
xet
 Community
anirvankrishna commited on
Commit
ae75f2f
·
verified ·
1 Parent(s): 0a47f57

Upload Qwen2ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +61 -61
  2. generation_config.json +14 -14
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,61 +1,61 @@
1
- {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "dtype": "float16",
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 1536,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 8960,
13
- "layer_types": [
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
- "full_attention"
42
- ],
43
- "max_position_embeddings": 32768,
44
- "max_window_layers": 21,
45
- "model_type": "qwen2",
46
- "num_attention_heads": 12,
47
- "num_hidden_layers": 28,
48
- "num_key_value_heads": 2,
49
- "pad_token_id": null,
50
- "rms_norm_eps": 1e-06,
51
- "rope_parameters": {
52
- "rope_theta": 1000000.0,
53
- "rope_type": "default"
54
- },
55
- "sliding_window": null,
56
- "tie_word_embeddings": true,
57
- "transformers_version": "5.3.0",
58
- "use_cache": true,
59
- "use_sliding_window": false,
60
- "vocab_size": 151936
61
- }
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
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
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": true,
57
+ "transformers_version": "5.0.0",
58
+ "use_cache": true,
59
+ "use_sliding_window": false,
60
+ "vocab_size": 151936
61
+ }
generation_config.json CHANGED
@@ -1,14 +1,14 @@
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
- "repetition_penalty": 1.1,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "5.3.0"
14
- }
 
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
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "5.0.0"
14
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24563aff08687bbfa110cb41d367849a8ef7e47a73e00a1e1ec1316e6130bacc
3
  size 3087466808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0846d178c934491bb1414526ce51ce1196cab3b53b96e1b065d133212732b8d1
3
  size 3087466808