Text Generation
Transformers
PyTorch
lfm2_vl
image-text-to-text
bf16
iris-3b
full-precision
vllm
xinference
custom_code
Instructions to use rty813/iris-3b-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rty813/iris-3b-bf16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rty813/iris-3b-bf16", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("rty813/iris-3b-bf16", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("rty813/iris-3b-bf16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use rty813/iris-3b-bf16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rty813/iris-3b-bf16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rty813/iris-3b-bf16", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rty813/iris-3b-bf16
- SGLang
How to use rty813/iris-3b-bf16 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 "rty813/iris-3b-bf16" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rty813/iris-3b-bf16", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "rty813/iris-3b-bf16" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rty813/iris-3b-bf16", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rty813/iris-3b-bf16 with Docker Model Runner:
docker model run hf.co/rty813/iris-3b-bf16
Download config.json from rty813/iris-3b-bf16: direct link, hf CLI and curl.
- Browser
- Download file 2.77 kB
-
https://huggingface.co/rty813/iris-3b-bf16/resolve/main/config.json
- Command line
-
hf download hf://rty813/iris-3b-bf16/config.json
-
curl -L -o config.json https://huggingface.co/rty813/iris-3b-bf16/resolve/main/config.json
2.77 kB
| { | |
| "architectures": [ | |
| "Lfm2VlForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoModel": "modeling_d1.D1Model" | |
| }, | |
| "bos_token_id": 124894, | |
| "do_image_splitting": true, | |
| "do_resize": true, | |
| "downsample_factor": 2, | |
| "dtype": "bfloat16", | |
| "encoder_patch_size": 16, | |
| "eos_token_id": 124900, | |
| "image_token_id": 124907, | |
| "max_image_tokens": 256, | |
| "max_num_patches": 1024, | |
| "max_pixels_tolerance": 2.0, | |
| "max_tiles": 10, | |
| "min_image_tokens": 64, | |
| "min_tiles": 2, | |
| "model_type": "lfm2_vl", | |
| "pad_token_id": 124893, | |
| "projector_bias": true, | |
| "projector_hidden_act": "gelu", | |
| "projector_hidden_size": 2048, | |
| "projector_use_layernorm": false, | |
| "text_config": { | |
| "architectures": [ | |
| "Lfm2ForCausalLM" | |
| ], | |
| "block__name_mlp": "parallel_mlp_merged", | |
| "block_auto_adjust_ff_dim": false, | |
| "block_dim": 2048, | |
| "block_ffn_dim_multiplier": 1.0, | |
| "block_multiple_of": 256, | |
| "block_norm_eps": 1e-05, | |
| "block_use_swiglu": true, | |
| "bos_token_id": 124894, | |
| "conv_L_cache": 3, | |
| "conv_bias": false, | |
| "conv_dim": 2048, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 124900, | |
| "full_attn_idxs": null, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10752, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "model_type": "lfm2", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_heads": 32, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 8, | |
| "output_softcap": 0.0, | |
| "pad_token_id": 124893, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "use_pos_enc": true, | |
| "vocab_size": 128000 | |
| }, | |
| "tie_word_embeddings": true, | |
| "tile_size": 512, | |
| "transformers_version": "5.14.1", | |
| "use_image_special_tokens": true, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip2_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_patches": 256, | |
| "patch_size": 16, | |
| "vision_use_head": false | |
| } | |
| } | |