Image-Text-to-Text
Transformers
Safetensors
trinity_vlm
text-generation
vision-language-model
multimodal
custom_code
trinity
moondream
conversational
Instructions to use NyxKrage/TrinityVLM-Nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NyxKrage/TrinityVLM-Nano with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="NyxKrage/TrinityVLM-Nano", trust_remote_code=True) 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("NyxKrage/TrinityVLM-Nano", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use NyxKrage/TrinityVLM-Nano with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NyxKrage/TrinityVLM-Nano" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NyxKrage/TrinityVLM-Nano", "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/NyxKrage/TrinityVLM-Nano
- SGLang
How to use NyxKrage/TrinityVLM-Nano 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 "NyxKrage/TrinityVLM-Nano" \ --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": "NyxKrage/TrinityVLM-Nano", "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 "NyxKrage/TrinityVLM-Nano" \ --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": "NyxKrage/TrinityVLM-Nano", "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 NyxKrage/TrinityVLM-Nano with Docker Model Runner:
docker model run hf.co/NyxKrage/TrinityVLM-Nano
| { | |
| "architectures": [ | |
| "TrinityVLMForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_trinity_vlm.TrinityVLMConfig", | |
| "AutoModelForCausalLM": "modeling_trinity_vlm.TrinityVLMForConditionalGeneration" | |
| }, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "enable_grouped_moe": true, | |
| "eos_token_id": 3, | |
| "hidden_size": 1024, | |
| "image_end_token": "<|vision_end|>", | |
| "image_end_token_id": 200001, | |
| "image_seq_len": 729, | |
| "image_start_token": "<|vision_start|>", | |
| "image_start_token_id": 200000, | |
| "image_token": "<|image_pad|>", | |
| "image_token_id": 200002, | |
| "model_type": "trinity_vlm", | |
| "output_router_logits": false, | |
| "pad_token_id": 12, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 3, | |
| "global_attn_every_n_layers": 4, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_types": [ | |
| "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", | |
| "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": 131072, | |
| "model_type": "afmoe", | |
| "moe_intermediate_size": 256, | |
| "mup_enabled": true, | |
| "n_group": 1, | |
| "num_attention_heads": 8, | |
| "num_dense_layers": 2, | |
| "num_expert_groups": 1, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 56, | |
| "num_key_value_heads": 2, | |
| "num_limited_groups": 1, | |
| "num_shared_experts": 1, | |
| "pad_token_id": 12, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "route_norm": true, | |
| "route_scale": 2.826, | |
| "score_func": "sigmoid", | |
| "sliding_window": 2048, | |
| "tie_word_embeddings": false, | |
| "topk_group": 1, | |
| "use_cache": true, | |
| "vocab_size": 200192 | |
| }, | |
| "transformers_version": "5.5.3", | |
| "vision_config": { | |
| "crop_size": 378, | |
| "enc_dim": 1152, | |
| "enc_ff_dim": 4304, | |
| "enc_n_heads": 16, | |
| "enc_n_layers": 27, | |
| "enc_patch_size": 14, | |
| "in_channels": 3, | |
| "max_crops": 12, | |
| "overlap_margin": 4, | |
| "proj_inner_dim": 8192, | |
| "proj_out_dim": 2048, | |
| "projector_hidden_dim": 2048 | |
| }, | |
| "vision_feature_dim": 2048, | |
| "vocab_size": 200192 | |
| } | |