Image-Text-to-Text
Transformers
Safetensors
hy_v4_vl
hunyuan
hy4
Mixture of Experts
multimodal
pretrained
conversational
Instructions to use tencent/Hy4-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Hy4-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="tencent/Hy4-base") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("tencent/Hy4-base") model = AutoModelForMultimodalLM.from_pretrained("tencent/Hy4-base", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use tencent/Hy4-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tencent/Hy4-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/Hy4-base", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/tencent/Hy4-base
- SGLang
How to use tencent/Hy4-base with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "tencent/Hy4-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/Hy4-base", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "tencent/Hy4-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/Hy4-base", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use tencent/Hy4-base with Docker Model Runner:
docker model run hf.co/tencent/Hy4-base
Download config.json from tencent/Hy4-base: direct link, hf CLI and curl.
- Browser
- Download file 7.38 kB
-
https://huggingface.co/tencent/Hy4-base/resolve/main/config.json
- Command line
-
hf download hf://tencent/Hy4-base/config.json
-
curl -L -o config.json https://huggingface.co/tencent/Hy4-base/resolve/main/config.json
7.38 kB
| { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bitwise_backward_align": false, | |
| "bos_token_id": null, | |
| "enable_ihc": true, | |
| "enable_lm_head_fp32": true, | |
| "eod_token_id": 120020, | |
| "eos_token_id": 120020, | |
| "gated_mla": true, | |
| "gating_type": "elementwise", | |
| "hc_eps": 1e-06, | |
| "hc_magnitude": 2.0, | |
| "hc_mult": 4, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "index_head_dim": 128, | |
| "index_n_heads": 32, | |
| "index_topk": 2048, | |
| "initializer_range": 0.006, | |
| "intermediate_size": 18432, | |
| "kv_lora_rank": 512, | |
| "layer_types": [ | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention", | |
| "deepseek_sparse_attention" | |
| ], | |
| "indexer_types": [ | |
| "full", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full", | |
| "shared", | |
| "shared", | |
| "shared", | |
| "full" | |
| ], | |
| "learnable_sink": true, | |
| "learnable_sink_init": 0.0, | |
| "max_position_embeddings": 1048576, | |
| "mlp_layer_types": [ | |
| "dense", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse" | |
| ], | |
| "model_type": "hy_v4_vl", | |
| "moe_intermediate_size": 2048, | |
| "n_group": 1, | |
| "n_routed_experts": 256, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 64, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 78, | |
| "num_key_value_heads": 8, | |
| "num_nextn_predict_layers": 0, | |
| "pad_token_id": null, | |
| "q_lora_rank": 2048, | |
| "qk_head_dim": 256, | |
| "qk_nope_head_dim": 192, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 10000000, | |
| "rope_type": "default", | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 12, | |
| 10, | |
| 10 | |
| ] | |
| }, | |
| "routed_scaling_factor": 2.827, | |
| "swiglu_limit": 10.0, | |
| "tie_word_embeddings": false, | |
| "topk_group": 1, | |
| "transformers_version": "5.24.0", | |
| "dtype": "bfloat16", | |
| "use_cache": true, | |
| "v_head_dim": 256, | |
| "vocab_size": 120832, | |
| "first_k_dense_replace": 1, | |
| "qk_norm": true, | |
| "architectures": [ | |
| "HYV4VLForConditionalGeneration" | |
| ], | |
| "vision_config": { | |
| "add_patchemb_bias": true, | |
| "attention_dropout": 0.0, | |
| "cat_extra_token": 0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 1536, | |
| "img_max_token_num": 4096, | |
| "intermediate_size": 6144, | |
| "interpolate_mode": "bilinear", | |
| "max_image_size": 2048, | |
| "max_vit_seq_len": 16384, | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 40, | |
| "out_hidden_size": 6144, | |
| "patch_size": 16, | |
| "rms_norm_eps": 1e-05, | |
| "temporal_patch_size": 1, | |
| "spatial_patch_size": 1, | |
| "spatial_merge_size": 2, | |
| "perceive_post_norm": false, | |
| "video_spatial_compression": false, | |
| "video_temporal_compression": false, | |
| "projector_type": "rmsnorm_mlp_adapter" | |
| }, | |
| "image_start_token_id": 120118, | |
| "image_end_token_id": 120119, | |
| "image_token_id": 120120, | |
| "image_newline_token_id": 120121, | |
| "video_token_id": 120124, | |
| "video_start_token_id": 120122, | |
| "video_end_token_id": 120123 | |
| } | |