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
4fa974c
·
verified ·
1 Parent(s): 5e46838

Update config.json

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