Hugging Face's logo

marin-community
/
marin-32b-base

Text Generation
Transformers
Safetensors
English
qwen3
text-generation-inference
Model card Files
xet
Community
3
WillHeld commited on
Commit
8aeba56
·
verified ·
1 Parent(s): c48cd94

Prettify Config.json

Browse files
Files changed (1) hide show
  1. config.json +161 -1
config.json CHANGED
@@ -1 +1,161 @@
1
- {"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 27648, "num_hidden_layers": 64, "num_attention_heads": 40, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "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, "layer_types": ["full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention"], "return_dict": true, "output_hidden_states": false, "torchscript": false, "torch_dtype": null, "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, "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "task_specific_params": null, "problem_type": null, "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, "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], "_name_or_path": "", "transformers_version": "4.55.4", "no_bias": true, "tf_legacy_loss": false, "use_bfloat16": false, "model_type": "qwen3", "output_attentions": false}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 128256,
3
+ "max_position_embeddings": 4096,
4
+ "hidden_size": 5120,
5
+ "intermediate_size": 27648,
6
+ "num_hidden_layers": 64,
7
+ "num_attention_heads": 40,
8
+ "use_sliding_window": false,
9
+ "sliding_window": null,
10
+ "max_window_layers": 28,
11
+ "num_key_value_heads": 8,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "initializer_range": 0.02,
15
+ "rms_norm_eps": 0.00001,
16
+ "use_cache": true,
17
+ "rope_theta": 500000,
18
+ "rope_scaling": {
19
+ "factor": 8,
20
+ "low_freq_factor": 1,
21
+ "high_freq_factor": 4,
22
+ "original_max_position_embeddings": 8192,
23
+ "rope_type": "llama3"
24
+ },
25
+ "attention_bias": false,
26
+ "attention_dropout": 0,
27
+ "layer_types": [
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
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention"
92
+ ],
93
+ "return_dict": true,
94
+ "output_hidden_states": false,
95
+ "torchscript": false,
96
+ "torch_dtype": null,
97
+ "pruned_heads": {},
98
+ "tie_word_embeddings": false,
99
+ "chunk_size_feed_forward": 0,
100
+ "is_encoder_decoder": false,
101
+ "is_decoder": false,
102
+ "cross_attention_hidden_size": null,
103
+ "add_cross_attention": false,
104
+ "tie_encoder_decoder": false,
105
+ "architectures": [
106
+ "LlamaForCausalLM"
107
+ ],
108
+ "finetuning_task": null,
109
+ "id2label": {
110
+ "0": "LABEL_0",
111
+ "1": "LABEL_1"
112
+ },
113
+ "label2id": {
114
+ "LABEL_0": 0,
115
+ "LABEL_1": 1
116
+ },
117
+ "task_specific_params": null,
118
+ "problem_type": null,
119
+ "tokenizer_class": null,
120
+ "prefix": null,
121
+ "bos_token_id": 128000,
122
+ "pad_token_id": null,
123
+ "eos_token_id": 128001,
124
+ "sep_token_id": null,
125
+ "decoder_start_token_id": 128000,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "do_sample": false,
129
+ "early_stopping": false,
130
+ "num_beams": 1,
131
+ "num_beam_groups": 1,
132
+ "diversity_penalty": 0,
133
+ "temperature": 1,
134
+ "top_k": 50,
135
+ "top_p": 1,
136
+ "typical_p": 1,
137
+ "repetition_penalty": 1,
138
+ "length_penalty": 1,
139
+ "no_repeat_ngram_size": 0,
140
+ "encoder_no_repeat_ngram_size": 0,
141
+ "bad_words_ids": null,
142
+ "num_return_sequences": 1,
143
+ "output_scores": false,
144
+ "return_dict_in_generate": false,
145
+ "forced_bos_token_id": null,
146
+ "forced_eos_token_id": null,
147
+ "remove_invalid_values": false,
148
+ "exponential_decay_length_penalty": null,
149
+ "suppress_tokens": null,
150
+ "begin_suppress_tokens": [
151
+ 128000,
152
+ 128001
153
+ ],
154
+ "_name_or_path": "",
155
+ "transformers_version": "4.55.4",
156
+ "no_bias": true,
157
+ "tf_legacy_loss": false,
158
+ "use_bfloat16": false,
159
+ "model_type": "qwen3",
160
+ "output_attentions": false
161
+ }