Image-Text-to-Text
Transformers
Safetensors
English
Chinese
dots_vlm
text-generation
multimodal
vision-language
chat
conversational
fp8
Instructions to use dots-studio/dots.vlm1.inst with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dots-studio/dots.vlm1.inst with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="dots-studio/dots.vlm1.inst") 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)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("dots-studio/dots.vlm1.inst", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dots-studio/dots.vlm1.inst with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dots-studio/dots.vlm1.inst" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dots-studio/dots.vlm1.inst", "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/dots-studio/dots.vlm1.inst
- SGLang
How to use dots-studio/dots.vlm1.inst 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 "dots-studio/dots.vlm1.inst" \ --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": "dots-studio/dots.vlm1.inst", "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 "dots-studio/dots.vlm1.inst" \ --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": "dots-studio/dots.vlm1.inst", "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 dots-studio/dots.vlm1.inst with Docker Model Runner:
docker model run hf.co/dots-studio/dots.vlm1.inst
| { | |
| "architectures": [ | |
| "DotsVLMForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "aux_loss_alpha": 0.001, | |
| "bos_token_id": 0, | |
| "eos_token_id": 1, | |
| "ep_size": 1, | |
| "first_k_dense_replace": 3, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18432, | |
| "kv_lora_rank": 512, | |
| "max_position_embeddings": 163840, | |
| "model_type": "dots_vlm", | |
| "moe_intermediate_size": 2048, | |
| "moe_layer_freq": 1, | |
| "n_group": 8, | |
| "n_routed_experts": 256, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 61, | |
| "num_key_value_heads": 128, | |
| "num_nextn_predict_layers": 1, | |
| "pretraining_tp": 1, | |
| "q_lora_rank": 1536, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "beta_fast": 32, | |
| "beta_slow": 1, | |
| "factor": 40, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 10000, | |
| "routed_scaling_factor": 2.5, | |
| "scoring_func": "sigmoid", | |
| "seq_aux": true, | |
| "tie_word_embeddings": false, | |
| "quantization_config": { | |
| "activation_scheme": "dynamic", | |
| "fmt": "e4m3", | |
| "quant_method": "fp8", | |
| "weight_block_size": [ | |
| 128, | |
| 128 | |
| ], | |
| "modules_to_not_convert": [ | |
| "vision_tower", | |
| "visual_tokenizer", | |
| "vision_model", | |
| "vision_proj" | |
| ] | |
| }, | |
| "topk_group": 4, | |
| "topk_method": "noaux_tc", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.33.1", | |
| "use_cache": true, | |
| "v_head_dim": 128, | |
| "vocab_size": 129280, | |
| "image_token_id": 128815, | |
| "video_token_id": 128836, | |
| "vision_config": { | |
| "embed_dim": 1536, | |
| "hidden_size": 7168, | |
| "intermediate_size": 4224, | |
| "num_hidden_layers": 42, | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "patch_size": 14, | |
| "post_norm": true, | |
| "rms_norm_eps": 1e-05, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 1, | |
| "use_bias": false, | |
| "attn_implementation": "flash_attention_2", | |
| "init_merger_std": 0.02, | |
| "initializer_range": 0.02, | |
| "is_causal": false | |
| } | |
| } |