Hugging Face's logo

axel-darmouni
/
smolvlm-instruct-thinking

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
idefics3
Generated from Trainer
trl
sft
conversational
Inference Endpoints
Model card Files Metrics Community
smolvlm-instruct-thinking
File size: 3,775 Bytes 
020110c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
 
{
  "_name_or_path": "HuggingFaceTB/SmolVLM-Instruct",
  "architectures": [
    "Idefics3ForConditionalGeneration"
  ],
  "image_seq_len": 81,
  "image_token_id": 49153,
  "model_type": "idefics3",
  "pad_token_id": 128002,
  "scale_factor": 3,
  "text_config": {
    "_flash_attn_2_enabled": true,
    "_name_or_path": "/fsx/m4/experiments/local_experiment_dir/s3_async_temporary_checkpoint_folder/tr_324_opt_400/unwrapped_model",
    "architectures": [
      "VLlama3ForCausalLM"
    ],
    "bos_token_id": 0,
    "eos_token_id": 0,
    "head_dim": 64,
    "hidden_size": 2048,
    "intermediate_size": 8192,
    "max_position_embeddings": 16384,
    "model_type": "llama",
    "neftune_noise_alpha": 0.0,
    "num_hidden_layers": 24,
    "pad_token_id": 2,
    "perceiver_config": {
      "_attn_implementation_autoset": false,
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_dropout": 0.0,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_act": "silu",
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "vllama3",
      "no_repeat_ngram_size": 0,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_key_value_heads": 1,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "qk_layer_norms_perceiver": false,
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "resampler_depth": 6,
      "resampler_head_dim": 96,
      "resampler_n_heads": 16,
      "resampler_n_latents": 64,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "transformers_version": "4.46.0",
      "typical_p": 1.0,
      "use_bfloat16": false
    },
    "qk_layer_norms": false,
    "rms_norm_eps": 1e-05,
    "rope_theta": 273768.0,
    "torch_dtype": "bfloat16",
    "use_resampler": false,
    "vocab_size": 49155
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers.js_config": {
    "dtype": {
      "decoder_model_merged": "q4",
      "embed_tokens": "auto",
      "vision_encoder": "auto"
    },
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vision_config": {
    "image_size": 384,
    "intermediate_size": 4304,
    "max_image_size": {
      "longest_edge": 384
    },
    "model_type": "idefics3_vision",
    "num_hidden_layers": 27,
    "patch_size": 14,
    "size": {
      "longest_edge": 1920
    },
    "tie_word_embeddings": false
  },
  "vocab_size": 49155
}