Video-Text-to-Text
MLX
Safetensors
English
qwen2_vl
apple-silicon
video-captioning
qwen2-vl
tarsier
4-bit precision
Instructions to use viavicdev/Tarsier2-Recap-7b-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use viavicdev/Tarsier2-Recap-7b-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Tarsier2-Recap-7b-MLX-4bit viavicdev/Tarsier2-Recap-7b-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
File size: 3,932 Bytes
99d176c | 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 | {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"generation_config": {
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151645,
"transformers_version": "4.47.0",
"use_cache": true
},
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2_vl",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"quantization": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"rms_norm_eps": 1e-06,
"rope_scaling": {
"type": "mrope",
"mrope_section": [
16,
24,
24
]
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"_attn_implementation_autoset": false,
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attn_implementation": "flash_attention_2",
"auto_map": {
"AutoConfig": "models--modeling_qwen2_vl_fast.Qwen2VLVisionConfig",
"AutoModel": "models--modeling_qwen2_vl_fast.Qwen2VisionTransformerPretrainedModel"
},
"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,
"depth": 32,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"embed_dim": 1280,
"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": "quick_gelu",
"hidden_size": 3584,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"in_channels": 3,
"in_chans": 3,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"mlp_ratio": 4,
"model_type": "qwen2_vl",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 16,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"temporal_patch_size": 2,
"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,
"typical_p": 1.0,
"use_bfloat16": false
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
} |