Hugging Face's logo

ZJU-AI4H
/
Hulu-Med-14B

Image-Text-to-Text
Transformers
Safetensors
PyTorch
hulumed_qwen3
text-generation
medical
multimodal
vision-language-model
image-to-text
video-understanding
3d-understanding
qwen
conversational
custom_code
Model card Files
xet
Community
2
Hulu-Med-14B
File size: 3,386 Bytes 
c8886b4
d8e2cf1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
{
    "architectures": [
      "HulumedQwen3ForCausalLM"
    ],
    "auto_map": {
          "AutoConfig": "configuration_hulumed_qwen3.HulumedQwen3Config",
          "AutoModelForCausalLM": "modeling_hulumed_qwen3.HulumedQwen3ForCausalLM"
      },
    "vocab_size": 151936,
    "max_position_embeddings": 40960,
    "hidden_size": 5120,
    "intermediate_size": 17408,
    "num_hidden_layers": 40,
    "num_attention_heads": 40,
    "use_sliding_window": false,
    "sliding_window": null,
    "max_window_layers": 40,
    "num_key_value_heads": 8,
    "head_dim": 128,
    "hidden_act": "silu",
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-06,
    "use_cache": true,
    "rope_theta": 1000000,
    "rope_scaling": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "return_dict": true,
    "output_hidden_states": false,
    "output_attentions": false,
    "torchscript": false,
    "torch_dtype": "bfloat16",
    "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": null,
    "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": 151643,
    "pad_token_id": null,
    "eos_token_id": 151645,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "task_specific_params": null,
    "problem_type": null,
    "_attn_implementation_autoset": true,
    "transformers_version": "4.51.2",
    "decoder_sparse_step": 1,
    "image_aspect_ratio": "avt",
    "image_size": -1,
    "image_token_index": 151669,
    "image_token_length": 1,
    "is_alignment": false,
    "llm_lr": 5e-05,
    "max_frames": 180,
    "mlp_only_layers": [],
    "mm_hidden_size": 1152,
    "mm_projector_lr": 1e-05,
    "mm_projector_type": "mlp2x_gelu",
    "model_type": "hulumed_qwen3",
    "moe_intermediate_size": 768,
    "norm_topk_prob": false,
    "num_experts": 128,
    "num_experts_per_tok": 8,
    "output_router_logits": false,
    "router_aux_loss_coef": 0.001,
    "tokenizer_model_max_length": 16384,
    "tokenizer_padding_side": "right",
    "use_token_compression": false,
    "vision_encoder_config": {
      "hidden_size": 1152,
      "intermediate_size": 4304,
      "model_type": "hulumed_vision_encoder",
      "num_attention_heads": 16,
      "num_hidden_layers": 27,
      "patch_size": 14
    }
  }