Hugging Face's logo

chest2vec
/
chest2vec_0.6B

Feature Extraction
Transformers
Safetensors
chest2vec
text-embeddings
retrieval
radiology
chest
qwen
custom_code
Model card Files
xet
 Community
lukeingawesome commited on
Commit
34c61c6
·
verified ·
1 Parent(s): 9286661

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +131 -10
config.json CHANGED
@@ -1,14 +1,135 @@
1
  {
2
- "model_type": "chest2vec",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "architectures": [
4
- "Chest2VecModel"
5
  ],
6
- "auto_map": {
7
- "AutoConfig": "configuration_chest2vec.Chest2VecConfig",
8
- "AutoModel": "modeling_chest2vec.Chest2VecModel"
 
 
 
 
 
9
  },
10
- "base_model": "Qwen/Qwen3-Embedding-0.6B",
11
- "adapter_subdir": "contrastive",
12
- "require_flash_attention_2": true,
13
- "default_max_len": 512
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "model_type": "chest2vec",
3
+ "architectures": [
4
+ "Chest2VecModel"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_chest2vec.Chest2VecConfig",
8
+ "AutoModel": "modeling_chest2vec.Chest2VecModel"
9
+ },
10
+ "base_model": "Qwen/Qwen3-Embedding-0.6B",
11
+ "encoder_config": {
12
+ "vocab_size": 151669,
13
+ "max_position_embeddings": 32768,
14
+ "hidden_size": 1024,
15
+ "intermediate_size": 3072,
16
+ "num_hidden_layers": 28,
17
+ "num_attention_heads": 16,
18
+ "use_sliding_window": false,
19
+ "sliding_window": null,
20
+ "max_window_layers": 28,
21
+ "num_key_value_heads": 8,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "initializer_range": 0.02,
25
+ "rms_norm_eps": 1e-06,
26
+ "use_cache": true,
27
+ "rope_theta": 1000000,
28
+ "rope_scaling": null,
29
+ "attention_bias": false,
30
+ "attention_dropout": 0.0,
31
+ "layer_types": [
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
+ ],
61
+ "return_dict": true,
62
+ "output_hidden_states": false,
63
+ "torchscript": false,
64
+ "dtype": "bfloat16",
65
+ "pruned_heads": {},
66
+ "tie_word_embeddings": true,
67
+ "chunk_size_feed_forward": 0,
68
+ "is_encoder_decoder": false,
69
+ "is_decoder": false,
70
+ "cross_attention_hidden_size": null,
71
+ "add_cross_attention": false,
72
+ "tie_encoder_decoder": false,
73
  "architectures": [
74
+ "Qwen3ForCausalLM"
75
  ],
76
+ "finetuning_task": null,
77
+ "id2label": {
78
+ "0": "LABEL_0",
79
+ "1": "LABEL_1"
80
+ },
81
+ "label2id": {
82
+ "LABEL_0": 0,
83
+ "LABEL_1": 1
84
  },
85
+ "task_specific_params": null,
86
+ "problem_type": null,
87
+ "tokenizer_class": null,
88
+ "prefix": null,
89
+ "bos_token_id": 151643,
90
+ "pad_token_id": null,
91
+ "eos_token_id": 151643,
92
+ "sep_token_id": null,
93
+ "decoder_start_token_id": null,
94
+ "max_length": 20,
95
+ "min_length": 0,
96
+ "do_sample": false,
97
+ "early_stopping": false,
98
+ "num_beams": 1,
99
+ "temperature": 1.0,
100
+ "top_k": 50,
101
+ "top_p": 1.0,
102
+ "typical_p": 1.0,
103
+ "repetition_penalty": 1.0,
104
+ "length_penalty": 1.0,
105
+ "no_repeat_ngram_size": 0,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "bad_words_ids": null,
108
+ "num_return_sequences": 1,
109
+ "output_scores": false,
110
+ "return_dict_in_generate": false,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "remove_invalid_values": false,
114
+ "exponential_decay_length_penalty": null,
115
+ "suppress_tokens": null,
116
+ "begin_suppress_tokens": null,
117
+ "num_beam_groups": 1,
118
+ "diversity_penalty": 0.0,
119
+ "_name_or_path": "Qwen/Qwen3-Embedding-0.6B",
120
+ "transformers_version": "4.57.3",
121
+ "model_type": "qwen3",
122
+ "tf_legacy_loss": false,
123
+ "use_bfloat16": false,
124
+ "output_attentions": false
125
+ },
126
+ "hidden_size": 1024,
127
+ "default_max_len": 512,
128
+ "pooling": "last_token",
129
+ "attn_implementation": "sdpa",
130
+ "matryoshka_dims": [
131
+ 256,
132
+ 512
133
+ ],
134
+ "torch_dtype": "float32"
135
+ }