Image-Text-to-Text
Transformers
Safetensors
dots3_note
text-generation
dots3
dots3-note
audio
multimodal
long-context
agentic
conversational
Eval Results
Instructions to use dots-studio/dots3-note-prev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dots-studio/dots3-note-prev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="dots-studio/dots3-note-prev") 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/dots3-note-prev", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dots-studio/dots3-note-prev with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dots-studio/dots3-note-prev" # 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/dots3-note-prev", "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/dots3-note-prev
- SGLang
How to use dots-studio/dots3-note-prev 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/dots3-note-prev" \ --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/dots3-note-prev", "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/dots3-note-prev" \ --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/dots3-note-prev", "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/dots3-note-prev with Docker Model Runner:
docker model run hf.co/dots-studio/dots3-note-prev
| { | |
| "architectures": [ | |
| "Dots3NoteForCausalLM" | |
| ], | |
| "apply_mla_qkv_lora_rescale": true, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_gate_type": "headwise", | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151668, | |
| "first_k_dense_replace": 1, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "index_head_dim": 128, | |
| "index_n_heads": 64, | |
| "index_topk": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "kv_lora_rank": 512, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 524288, | |
| "model_type": "dots3_note", | |
| "moe_intermediate_size": 1536, | |
| "moe_layer_freq": 1, | |
| "n_routed_experts": 256, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 46, | |
| "num_key_value_heads": 128, | |
| "pretraining_tp": 1, | |
| "q_lora_rank": 1024, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 80000000.0, | |
| "routed_scaling_factor": 1.0, | |
| "scoring_func": "sigmoid", | |
| "sliding_window_size": 513, | |
| "swa_attention_gate_type": "headwise", | |
| "swa_kv_lora_rank": 1024, | |
| "swa_num_attention_heads": 64, | |
| "swa_num_key_value_heads": 64, | |
| "swa_q_lora_rank": 1024, | |
| "swa_qk_nope_head_dim": 192, | |
| "swa_qk_rope_head_dim": 64, | |
| "swa_rope_theta": 50000.0, | |
| "swa_v_head_dim": 128, | |
| "tie_word_embeddings": false, | |
| "topk_method": "noaux_tc", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.0", | |
| "use_cache": true, | |
| "v_head_dim": 128, | |
| "vocab_size": 152064, | |
| "vision_config": { | |
| "embed_dim": 1536, | |
| "hidden_size": 5120, | |
| "intermediate_size": 4224, | |
| "moe_intermediate_size": 2112, | |
| "num_hidden_layers": 42, | |
| "num_attention_heads": 24, | |
| "num_channels": 3, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 1, | |
| "rms_norm_eps": 1e-05, | |
| "use_bias": false, | |
| "use_qk_norm": true, | |
| "attn_implementation": "flash_attention_3", | |
| "initializer_range": 0.02, | |
| "is_causal": false, | |
| "post_norm": true, | |
| "pre_pixel_shuffle": true, | |
| "pyramid_num_routed": [ | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| -1, | |
| 4, | |
| 8, | |
| 12, | |
| 16, | |
| 20, | |
| 24, | |
| 28, | |
| 32, | |
| 36, | |
| 40, | |
| 44, | |
| 48, | |
| 52, | |
| 56, | |
| 60, | |
| 64, | |
| 64 | |
| ], | |
| "capacity_factor": 2, | |
| "router_scoring_func": "sigmoid", | |
| "router_scale": 1.0, | |
| "adapter_type": "patch_merger", | |
| "adapter_in_dim": 1536, | |
| "adapter_out_dim": 5120, | |
| "adapter_merge_size": 2 | |
| }, | |
| "audio_config": { | |
| "encoder_type": "dots", | |
| "whisper_config": { | |
| "d_model": 1280, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layers": 32, | |
| "num_mel_bins": 128, | |
| "max_source_positions": 6000, | |
| "activation_function": "swiglu" | |
| }, | |
| "use_conv2d_stem": true, | |
| "use_rope": true, | |
| "use_rms_norm": true, | |
| "use_causal": false, | |
| "downsample_hidden_size": 480, | |
| "conv_chunksize": 500, | |
| "conv_stem_gradient_checkpointing": true, | |
| "conv_bucket_step": 10, | |
| "conv_bucket_max_elements": 20000, | |
| "rope_parameters": { | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 10000.0 | |
| }, | |
| "merge_factor": 1, | |
| "chunk_seconds": 60, | |
| "whisper_adapter_in_dim": 1280, | |
| "whisper_adapter_out_dim": 5120, | |
| "sampling_rate": 16000, | |
| "audio_comp_start": "<|audio_comp_start|>", | |
| "audio_comp_span": "<|audio_comp_pad|>", | |
| "audio_comp_end": "<|audio_comp_end|>" | |
| } | |
| } | |