Hugging Face's logo

reaperdoesntknow
/
Symbiotic-Beta

Text Generation
Transformers
PyTorch
Safetensors
English
symbiotic-llm
Generated from Trainer
meta-math
qwen2
symbolic-ai
symbioticlm
conversational
Model card Files Community
1
reaperdoesntknow commited on
Commit
a99e502
·
verified ·
1 Parent(s): 848c62f

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +68 -77
config.json CHANGED
@@ -1,80 +1,71 @@
1
  {
2
  "architectures": [
3
  "Qwen2ForCausalLM"
4
- ],
5
- "return_dict": true,
6
- "output_hidden_states": false,
7
- "output_attentions": false,
8
- "torchscript": false,
9
- "torch_dtype": null,
10
- "use_bfloat16": false,
11
- "tf_legacy_loss": false,
12
- "pruned_heads": {},
13
- "tie_word_embeddings": true,
14
- "chunk_size_feed_forward": 64,
15
- "is_encoder_decoder": false,
16
- "is_decoder": false,
17
- "cross_attention_hidden_size": null,
18
- "add_cross_attention": false,
19
- "tie_encoder_decoder": false,
20
- "max_length": 512,
21
- "min_length": 64,
22
- "do_sample": true,
23
- "early_stopping": false,
24
- "num_beams": 1,
25
- "num_beam_groups": 1,
26
- "diversity_penalty": 0.0,
27
- "temperature": 1.0,
28
- "top_k": 50,
29
- "top_p": 0.90,
30
- "typical_p": 0.95,
31
- "repetition_penalty": 1.0,
32
- "length_penalty": 1.0,
33
- "no_repeat_ngram_size": 1,
34
- "encoder_no_repeat_ngram_size": 0,
35
- "bad_words_ids": null,
36
- "num_return_sequences": 1,
37
- "output_scores": false,
38
- "return_dict_in_generate": false,
39
- "forced_bos_token_id": null,
40
- "forced_eos_token_id": null,
41
- "remove_invalid_values": false,
42
- "exponential_decay_length_penalty": null,
43
- "suppress_tokens": null,
44
- "begin_suppress_tokens": null,
45
- "finetuning_task": null,
46
- "id2label": {
47
- "0": "LABEL_0",
48
- "1": "LABEL_1"
49
- },
50
- "label2id": {
51
- "LABEL_0": 0,
52
- "LABEL_1": 1
53
- },
54
- "tokenizer_class": null,
55
- "prefix": null,
56
- "bos_token_id": 2,
57
- "pad_token_id": 0,
58
- "eos_token_id": 3,
59
- "sep_token_id": null,
60
- "decoder_start_token_id": null,
61
- "task_specific_params": null,
62
- "problem_type": null,
63
- "_name_or_path": "",
64
- "_attn_implementation_autoset": true,
65
- "transformers_version": "4.51.3",
66
- "vocab_size": 37524,
67
- "d_model": 2048,
68
- "n_heads": 32,
69
- "n_layers": 16,
70
- "max_seq": 4096,
71
- "rope_base": 1000000.0,
72
- "dropout": 0.1,
73
- "adapters": [
74
- "lnn"
75
- ],
76
- "tie_embed": true,
77
- "use_flash": false,
78
- "model_type": "qwen2"
79
- }
80
-
 
1
  {
2
  "architectures": [
3
  "Qwen2ForCausalLM"
4
+ ],
5
+ "model_type": "qwen2",
6
+ "vocab_size": 37524,
7
+ "d_model": 2048,
8
+ "n_heads": 32,
9
+ "n_layers": 16,
10
+ "max_seq": 4096,
11
+ "rope_base": 1000000.0,
12
+ "dropout": 0.1,
13
+ "adapters": [
14
+ "lnn"
15
+ ],
16
+ "tie_embed": true,
17
+ "use_flash": false,
18
+ "return_dict": true,
19
+ "output_hidden_states": false,
20
+ "output_attentions": false,
21
+ "torchscript": false,
22
+ "torch_dtype": null,
23
+ "use_bfloat16": false,
24
+ "tf_legacy_loss": false,
25
+ "pruned_heads": {},
26
+ "tie_word_embeddings": true,
27
+ "chunk_size_feed_forward": 64,
28
+ "is_encoder_decoder": false,
29
+ "is_decoder": false,
30
+ "add_cross_attention": false,
31
+ "cross_attention_hidden_size": null,
32
+ "tie_encoder_decoder": false,
33
+ "max_length": 512,
34
+ "min_length": 64,
35
+ "do_sample": true,
36
+ "early_stopping": false,
37
+ "num_beams": 1,
38
+ "num_beam_groups": 1,
39
+ "diversity_penalty": 0.0,
40
+ "temperature": 1.0,
41
+ "top_k": 50,
42
+ "top_p": 0.9,
43
+ "typical_p": 0.95,
44
+ "repetition_penalty": 1.0,
45
+ "length_penalty": 1.0,
46
+ "no_repeat_ngram_size": 1,
47
+ "encoder_no_repeat_ngram_size": 0,
48
+ "bad_words_ids": null,
49
+ "num_return_sequences": 1,
50
+ "output_scores": false,
51
+ "return_dict_in_generate": false,
52
+ "forced_bos_token_id": null,
53
+ "forced_eos_token_id": null,
54
+ "remove_invalid_values": false,
55
+ "exponential_decay_length_penalty": null,
56
+ "suppress_tokens": null,
57
+ "begin_suppress_tokens": null,
58
+ "finetuning_task": null,
59
+ "tokenizer_class": "PreTrainedTokenizerFast",
60
+ "prefix": null,
61
+ "bos_token_id": 2,
62
+ "pad_token_id": 0,
63
+ "eos_token_id": 3,
64
+ "sep_token_id": null,
65
+ "decoder_start_token_id": null,
66
+ "task_specific_params": null,
67
+ "problem_type": null,
68
+ "_name_or_path": "",
69
+ "_attn_implementation_autoset": true,
70
+ "transformers_version": "4.51.3"
71
+ }