Download config.json from hf-tiny-v2/tiny-random-FastVlmModel: direct link, hf CLI and curl.
- Browser
- Download file 2.12 kB
-
https://huggingface.co/hf-tiny-v2/tiny-random-FastVlmModel/resolve/main/config.json
- Command line
-
hf download hf://hf-tiny-v2/tiny-random-FastVlmModel/config.json
-
curl -L -o config.json https://huggingface.co/hf-tiny-v2/tiny-random-FastVlmModel/resolve/main/config.json
2.12 kB
| { | |
| "architectures": [ | |
| "FastVlmModel" | |
| ], | |
| "dtype": "float32", | |
| "ignore_index": -100, | |
| "image_seq_length": 576, | |
| "image_token_index": 0, | |
| "model_type": "fast_vlm", | |
| "multimodal_projector_bias": true, | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "is_training": true, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 512, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151647 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.16.0.dev0", | |
| "vision_config": { | |
| "architecture": "fastvit_mci3", | |
| "do_pooling": true, | |
| "global_pool": "avg", | |
| "hidden_size": 32, | |
| "image_size": 16, | |
| "initializer_range": 0.02, | |
| "label_names": [ | |
| "LABEL_0", | |
| "LABEL_1" | |
| ], | |
| "model_args": { | |
| "downsamples": [ | |
| false, | |
| true | |
| ], | |
| "embed_dims": [ | |
| 8, | |
| 16 | |
| ], | |
| "inference_mode": true, | |
| "layers": [ | |
| 2, | |
| 2 | |
| ], | |
| "lkc_use_act": true, | |
| "mlp_ratios": [ | |
| 4, | |
| 4 | |
| ], | |
| "pos_embs": [ | |
| null, | |
| null | |
| ], | |
| "se_downsamples": [ | |
| false, | |
| false | |
| ], | |
| "stem_use_scale_branch": false, | |
| "token_mixers": [ | |
| "repmixer", | |
| "repmixer" | |
| ] | |
| }, | |
| "model_type": "timm_wrapper", | |
| "num_channels": 3, | |
| "num_classes": 2, | |
| "patch_size": 8 | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "full" | |
| } | |