Hugging Face's logo

ggcristian
/
TinyEmo-CLIP-TinyLlama-1_1-Syn

Image Classification
English
tinyemo
emotion
visual emotion recognition
affective computing
emotional classification
metric learning
Model card Files Community
TinyEmo-CLIP-TinyLlama-1_1-Syn
File size: 2,122 Bytes 
b9b09c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "architectures": [
    "TinyEmoForConditionalGeneration"
  ],
  "cache_dir": null,
  "connector_type": "mlp2x_gelu",
  "hidden_size": 2048,
  "ignore_index": -100,
  "image_aspect_ratio": "square",
  "image_token_index": -200,
  "llm_model_name_or_path": "apple/TinyLlama-1.1B-Chat-v1.0",
  "model_type": "tinyemo",
  "num_queries": 128,
  "num_resampler_layers": 3,
  "pad_token": "<|endoftext|>",
  "pad_token_id": 1,
  "resampler_hidden_size": 768,
  "text_config": {
    "_name_or_path": "apple/TinyLlama-1.1B-Chat-v1.0",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 5632,
    "max_position_embeddings": 2048,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 22,
    "num_key_value_heads": 4,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.35.0",
    "use_cache": true,
    "vocab_size": 32000
  },
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "tokenizer_use_fast": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.35.0",
  "tune_type_connector": "full",
  "tune_type_llm": "full",
  "tune_type_vision_tower": "frozen",
  "tune_vision_tower_from_layer": 0,
  "use_cache": true,
  "vision_config": {
    "_name_or_path": "openai/clip-vit-large-patch14",
    "architectures": [
      "CLIPModel"
    ],
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 224,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "patch",
  "vision_hidden_size": 1024,
  "vision_model_name_or_path": "openai/clip-vit-large-patch14",
  "vocab_size": 32000
}