Video-Text-to-Text
Transformers
Safetensors
English
Chinese
internvideo3
text-generation
video-understanding
multimodal
long-video
agent
custom_code
Instructions to use yanziang/InternVideo3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yanziang/InternVideo3-8B-Instruct with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("yanziang/InternVideo3-8B-Instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "InternVideo3ForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoModel": "modeling_internvideo3.InternVideo3Model", | |
| "AutoModelForCausalLM": "modeling_internvideo3.InternVideo3ForConditionalGeneration", | |
| "AutoConfig": "configuration_internvideo3.InternVideo3Config", | |
| "AutoProcessor": "processing_internvideo3.InternVideo3Processor" | |
| }, | |
| "dtype": "bfloat16", | |
| "image_token_id": 151655, | |
| "model_type": "internvideo3", | |
| "text_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 262144, | |
| "model_type": "internvideo3_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 32, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "use_cache": true, | |
| "vocab_size": 151936, | |
| "qk_rope_head_dim": 128, | |
| "qk_nope_head_dim": 128, | |
| "v_head_dim": 128, | |
| "q_lora_rank": null, | |
| "rope_interleave": true, | |
| "kv_lora_rank_list": [ | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896, | |
| 896 | |
| ], | |
| "qk_latent_layernorm": false | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.3", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 27, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "internvideo3", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 4096, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652 | |
| } |