Hugging Face's logo

jyc0325
/
Qwen2.5-7B-ORPO-code

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
orpo
conversational
text-generation-inference
Model card Files
xet
 Community
jyc0325 commited on
Commit
3a12477
·
verified ·
1 Parent(s): 8471ce1

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +105 -19
config.json CHANGED
@@ -1,29 +1,115 @@
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
- "max_position_embeddings": 32768,
13
- "max_window_layers": 28,
14
- "model_type": "qwen2",
15
- "num_attention_heads": 28,
16
  "num_hidden_layers": 28,
 
 
 
 
17
  "num_key_value_heads": 4,
 
 
18
  "rms_norm_eps": 1e-06,
 
19
  "rope_theta": 1000000.0,
20
- "sliding_window": 131072,
21
- "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.43.1",
24
- "use_cache": true,
25
- "use_sliding_window": false,
26
- "vocab_size": 152064,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "finetuned_from": "Qwen/Qwen2.5-7B-Instruct",
28
- "repo_creator": "jyc0325"
 
29
  }
 
1
  {
2
+ "vocab_size": 151665,
3
+ "max_position_embeddings": 32768,
 
 
 
 
 
4
  "hidden_size": 3584,
 
5
  "intermediate_size": 18944,
 
 
 
 
6
  "num_hidden_layers": 28,
7
+ "num_attention_heads": 28,
8
+ "use_sliding_window": false,
9
+ "sliding_window": null,
10
+ "max_window_layers": 28,
11
  "num_key_value_heads": 4,
12
+ "hidden_act": "silu",
13
+ "initializer_range": 0.02,
14
  "rms_norm_eps": 1e-06,
15
+ "use_cache": true,
16
  "rope_theta": 1000000.0,
17
+ "rope_scaling": null,
18
+ "attention_dropout": 0.0,
19
+ "layer_types": [
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
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention"
48
+ ],
49
+ "return_dict": true,
50
+ "output_hidden_states": false,
51
+ "torchscript": false,
52
  "torch_dtype": "bfloat16",
53
+ "use_bfloat16": false,
54
+ "tf_legacy_loss": false,
55
+ "pruned_heads": {},
56
+ "tie_word_embeddings": false,
57
+ "chunk_size_feed_forward": 0,
58
+ "is_encoder_decoder": false,
59
+ "is_decoder": false,
60
+ "cross_attention_hidden_size": null,
61
+ "add_cross_attention": false,
62
+ "tie_encoder_decoder": false,
63
+ "max_length": 20,
64
+ "min_length": 0,
65
+ "do_sample": false,
66
+ "early_stopping": false,
67
+ "num_beams": 1,
68
+ "num_beam_groups": 1,
69
+ "diversity_penalty": 0.0,
70
+ "temperature": 1.0,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "typical_p": 1.0,
74
+ "repetition_penalty": 1.0,
75
+ "length_penalty": 1.0,
76
+ "no_repeat_ngram_size": 0,
77
+ "encoder_no_repeat_ngram_size": 0,
78
+ "bad_words_ids": null,
79
+ "num_return_sequences": 1,
80
+ "output_scores": false,
81
+ "return_dict_in_generate": false,
82
+ "forced_bos_token_id": null,
83
+ "forced_eos_token_id": null,
84
+ "remove_invalid_values": false,
85
+ "exponential_decay_length_penalty": null,
86
+ "suppress_tokens": null,
87
+ "begin_suppress_tokens": null,
88
+ "architectures": [
89
+ "Qwen2ForCausalLM"
90
+ ],
91
+ "finetuning_task": null,
92
+ "id2label": {
93
+ "0": "LABEL_0",
94
+ "1": "LABEL_1"
95
+ },
96
+ "label2id": {
97
+ "LABEL_0": 0,
98
+ "LABEL_1": 1
99
+ },
100
+ "tokenizer_class": null,
101
+ "prefix": null,
102
+ "bos_token_id": 151643,
103
+ "pad_token_id": null,
104
+ "eos_token_id": 151645,
105
+ "sep_token_id": null,
106
+ "decoder_start_token_id": null,
107
+ "task_specific_params": null,
108
+ "problem_type": null,
109
+ "_name_or_path": "jyc0325/Qwen2.5-7B-ORPO-code",
110
+ "transformers_version": "4.53.0",
111
+ "model_type": "qwen2",
112
  "finetuned_from": "Qwen/Qwen2.5-7B-Instruct",
113
+ "repo_creator": "jyc0325",
114
+ "output_attentions": false
115
  }