Hugging Face's logo

WillHeld
/
ToMol-marin-1B

Safetensors
qwen3
Model card Files
xet
 Community
WillHeld commited on
Commit
c1727ed
·
verified ·
1 Parent(s): 1b33218

Fix architectures: LlamaForCausalLM -> Qwen3ForCausalLM

Browse files
Files changed (1) hide show
  1. config.json +117 -1
config.json CHANGED
@@ -1 +1,117 @@
1
- {"vocab_size": 6275, "max_position_embeddings": 4096, "hidden_size": 1920, "intermediate_size": 7680, "num_hidden_layers": 19, "num_attention_heads": 15, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "num_key_value_heads": 15, "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"], "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": null, "pruned_heads": {}, "tie_word_embeddings": true, "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": 1, "pad_token_id": 0, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": 1, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "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": [0, 1, 2], "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "transformers_version": "4.57.5", "no_bias": true, "tf_legacy_loss": false, "use_bfloat16": false, "model_type": "qwen3", "output_attentions": false}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 6275,
3
+ "max_position_embeddings": 4096,
4
+ "hidden_size": 1920,
5
+ "intermediate_size": 7680,
6
+ "num_hidden_layers": 19,
7
+ "num_attention_heads": 15,
8
+ "use_sliding_window": false,
9
+ "sliding_window": null,
10
+ "max_window_layers": 28,
11
+ "num_key_value_heads": 15,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "initializer_range": 0.02,
15
+ "rms_norm_eps": 1e-05,
16
+ "use_cache": true,
17
+ "rope_theta": 500000,
18
+ "rope_scaling": {
19
+ "factor": 8.0,
20
+ "low_freq_factor": 1.0,
21
+ "high_freq_factor": 4.0,
22
+ "original_max_position_embeddings": 8192,
23
+ "rope_type": "llama3"
24
+ },
25
+ "attention_bias": false,
26
+ "attention_dropout": 0.0,
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
+ ],
48
+ "return_dict": true,
49
+ "output_hidden_states": false,
50
+ "torchscript": false,
51
+ "dtype": null,
52
+ "pruned_heads": {},
53
+ "tie_word_embeddings": true,
54
+ "chunk_size_feed_forward": 0,
55
+ "is_encoder_decoder": false,
56
+ "is_decoder": false,
57
+ "cross_attention_hidden_size": null,
58
+ "add_cross_attention": false,
59
+ "tie_encoder_decoder": false,
60
+ "architectures": [
61
+ "Qwen3ForCausalLM"
62
+ ],
63
+ "finetuning_task": null,
64
+ "id2label": {
65
+ "0": "LABEL_0",
66
+ "1": "LABEL_1"
67
+ },
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1
71
+ },
72
+ "task_specific_params": null,
73
+ "problem_type": null,
74
+ "tokenizer_class": null,
75
+ "prefix": null,
76
+ "bos_token_id": 1,
77
+ "pad_token_id": 0,
78
+ "eos_token_id": 2,
79
+ "sep_token_id": null,
80
+ "decoder_start_token_id": 1,
81
+ "max_length": 20,
82
+ "min_length": 0,
83
+ "do_sample": false,
84
+ "early_stopping": false,
85
+ "num_beams": 1,
86
+ "temperature": 1.0,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "typical_p": 1.0,
90
+ "repetition_penalty": 1.0,
91
+ "length_penalty": 1.0,
92
+ "no_repeat_ngram_size": 0,
93
+ "encoder_no_repeat_ngram_size": 0,
94
+ "bad_words_ids": null,
95
+ "num_return_sequences": 1,
96
+ "output_scores": false,
97
+ "return_dict_in_generate": false,
98
+ "forced_bos_token_id": null,
99
+ "forced_eos_token_id": null,
100
+ "remove_invalid_values": false,
101
+ "exponential_decay_length_penalty": null,
102
+ "suppress_tokens": null,
103
+ "begin_suppress_tokens": [
104
+ 0,
105
+ 1,
106
+ 2
107
+ ],
108
+ "num_beam_groups": 1,
109
+ "diversity_penalty": 0.0,
110
+ "_name_or_path": "",
111
+ "transformers_version": "4.57.5",
112
+ "no_bias": true,
113
+ "tf_legacy_loss": false,
114
+ "use_bfloat16": false,
115
+ "model_type": "qwen3",
116
+ "output_attentions": false
117
+ }