Hugging Face's logo

marin-community
/
marin-8b-instruct

Text Generation
Safetensors
English
llama
conversational
Model card Files Community
WillHeld commited on
Commit
14127e0
·
verified ·
1 Parent(s): be5c78f

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +94 -1
config.json CHANGED
@@ -1 +1,94 @@
1
- {"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.51.3", "model_type": "llama"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 128256,
3
+ "max_position_embeddings": 4096,
4
+ "hidden_size": 4096,
5
+ "intermediate_size": 14336,
6
+ "num_hidden_layers": 32,
7
+ "num_attention_heads": 32,
8
+ "num_key_value_heads": 8,
9
+ "hidden_act": "silu",
10
+ "initializer_range": 0.02,
11
+ "rms_norm_eps": 0.00001,
12
+ "pretraining_tp": 1,
13
+ "use_cache": true,
14
+ "rope_theta": 500000,
15
+ "rope_scaling": {
16
+ "factor": 8.0,
17
+ "low_freq_factor": 1.0,
18
+ "high_freq_factor": 4.0,
19
+ "original_max_position_embeddings": 8192,
20
+ "rope_type": "llama3"
21
+ },
22
+ "attention_bias": false,
23
+ "attention_dropout": 0.0,
24
+ "mlp_bias": false,
25
+ "head_dim": 128,
26
+ "return_dict": true,
27
+ "output_hidden_states": false,
28
+ "output_attentions": false,
29
+ "torchscript": false,
30
+ "torch_dtype": null,
31
+ "use_bfloat16": false,
32
+ "tf_legacy_loss": false,
33
+ "pruned_heads": {},
34
+ "tie_word_embeddings": false,
35
+ "chunk_size_feed_forward": 0,
36
+ "is_encoder_decoder": false,
37
+ "is_decoder": false,
38
+ "cross_attention_hidden_size": null,
39
+ "add_cross_attention": false,
40
+ "tie_encoder_decoder": false,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "do_sample": false,
44
+ "early_stopping": false,
45
+ "num_beams": 1,
46
+ "num_beam_groups": 1,
47
+ "diversity_penalty": 0.0,
48
+ "temperature": 1.0,
49
+ "top_k": 50,
50
+ "top_p": 1.0,
51
+ "typical_p": 1.0,
52
+ "repetition_penalty": 1.0,
53
+ "length_penalty": 1.0,
54
+ "no_repeat_ngram_size": 0,
55
+ "encoder_no_repeat_ngram_size": 0,
56
+ "bad_words_ids": null,
57
+ "num_return_sequences": 1,
58
+ "output_scores": false,
59
+ "return_dict_in_generate": false,
60
+ "forced_bos_token_id": null,
61
+ "forced_eos_token_id": null,
62
+ "remove_invalid_values": false,
63
+ "exponential_decay_length_penalty": null,
64
+ "suppress_tokens": null,
65
+ "begin_suppress_tokens": [
66
+ 128000,
67
+ 128001
68
+ ],
69
+ "architectures": [
70
+ "LlamaForCausalLM"
71
+ ],
72
+ "finetuning_task": null,
73
+ "id2label": {
74
+ "0": "LABEL_0",
75
+ "1": "LABEL_1"
76
+ },
77
+ "label2id": {
78
+ "LABEL_0": 0,
79
+ "LABEL_1": 1
80
+ },
81
+ "tokenizer_class": null,
82
+ "prefix": null,
83
+ "bos_token_id": 128000,
84
+ "pad_token_id": null,
85
+ "eos_token_id": 128009,
86
+ "sep_token_id": null,
87
+ "decoder_start_token_id": 128000,
88
+ "task_specific_params": null,
89
+ "problem_type": null,
90
+ "_name_or_path": "",
91
+ "_attn_implementation_autoset": false,
92
+ "transformers_version": "4.51.3",
93
+ "model_type": "llama"
94
+ }