Instructions to use chibubu/bingo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chibubu/bingo with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("chibubu/bingo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from chibubu/bingo: direct link, hf CLI and curl.
- Browser
- Download file 3.72 kB
-
https://huggingface.co/chibubu/bingo/resolve/main/config.json
- Command line
-
hf download hf://chibubu/bingo/config.json
-
curl -L -o config.json https://huggingface.co/chibubu/bingo/resolve/main/config.json
3.72 kB
| { | |
| "architectures": [ | |
| "AudioVisualFlamingoForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "Qwen2AudioEncoder" | |
| ], | |
| "attention_dropout": 0.0, | |
| "d_model": 1280, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 32, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "max_source_positions": 1500, | |
| "model_type": "qwen2_audio_encoder", | |
| "num_mel_bins": 128, | |
| "scale_embedding": false | |
| }, | |
| "dtype": "bfloat16", | |
| "dynamic_s2": true, | |
| "encoder_text_token_ids": { | |
| "\n": [ | |
| 198 | |
| ] | |
| }, | |
| "image_encoder": { | |
| "_target_": "BasicImageEncoder" | |
| }, | |
| "interleaved_vis_aud_in_video": true, | |
| "load_audio_in_video": true, | |
| "media_token_ids": { | |
| "image": 151649, | |
| "sound": 151652, | |
| "video": 151650 | |
| }, | |
| "mm_vision_select_feature": "cls_patch", | |
| "mm_vision_select_layer": -2, | |
| "model_type": "audiovisualflamingo", | |
| "multimodal_projector_bias": true, | |
| "projector_bias": true, | |
| "s2_max_split_size": 448, | |
| "s2_resize_output_to_scale_idx": -1, | |
| "s2_scales": [ | |
| 448, | |
| 896, | |
| 1344 | |
| ], | |
| "sound_encoder": { | |
| "_target_": "BasicSoundEncoder", | |
| "embed_time": true, | |
| "end_tokens": null, | |
| "time_embed_type": "lang", | |
| "trope_dim": 128, | |
| "trope_theta": 50000 | |
| }, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 15300000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151661 | |
| }, | |
| "transformers_version": "5.7.0.dev0", | |
| "video_encoder": { | |
| "_target_": "TSPVideoEncoder", | |
| "embed_time": true, | |
| "end_tokens": null, | |
| "pool_sizes": [ | |
| [ | |
| 8, | |
| 1, | |
| 1 | |
| ] | |
| ], | |
| "time_embed_type": "lang", | |
| "trope_dim": 128, | |
| "trope_theta": 50000 | |
| }, | |
| "vision_config": { | |
| "architectures": [ | |
| "SiglipVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 448, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "vision_use_head": false | |
| } | |
| } | |