Image-Text-to-Text
Transformers
Safetensors
qwen3_5
clairic
cloudflare
systemone
multimodal
structured-output
information-extraction
custom-code
conversational
Instructions to use Cloudflare/clairic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cloudflare/clairic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Cloudflare/clairic") 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("Cloudflare/clairic") model = AutoModelForMultimodalLM.from_pretrained("Cloudflare/clairic", 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 Cloudflare/clairic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Cloudflare/clairic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "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/Cloudflare/clairic
- SGLang
How to use Cloudflare/clairic 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 "Cloudflare/clairic" \ --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": "Cloudflare/clairic", "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 "Cloudflare/clairic" \ --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": "Cloudflare/clairic", "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 Cloudflare/clairic with Docker Model Runner:
docker model run hf.co/Cloudflare/clairic
Download clairic_runtime/normalization.py from Cloudflare/clairic: direct link, hf CLI and curl.
- Browser
- Download file 1.44 kB
-
https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/normalization.py
- Command line
-
hf download hf://Cloudflare/clairic/clairic_runtime/normalization.py
-
curl -L -o normalization.py https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/normalization.py
1.44 kB
| """Public CUDA normalization with the model's residual precision.""" | |
| from __future__ import annotations | |
| import torch | |
| def _bf16_pair_sum(value: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]: | |
| """Recover BF16 operands for an FP32 sum of two BF16 residuals.""" | |
| if (value.is_cuda and value.dtype == torch.float32 and value.is_contiguous() | |
| and not torch.is_grad_enabled() and not torch.compiler.is_compiling()): | |
| from .kernels import bf16_pair_sum | |
| return bf16_pair_sum(value) | |
| limit = torch.finfo(torch.bfloat16).max | |
| high = value.clamp(-limit, limit).to(torch.bfloat16) | |
| low = (value - high.float()).to(torch.bfloat16) | |
| # Equal signed zeros keep the sign when the fused operation adds them. | |
| low = torch.where(value == 0, high, low) | |
| return high, low | |
| def rms_norm(value: torch.Tensor, weight: torch.Tensor, eps: float) -> torch.Tensor: | |
| """Normalize CUDA BF16 states or unrounded FP32 residual sums.""" | |
| from flashinfer.norm import gemma_fused_add_rmsnorm, gemma_rmsnorm | |
| shape = value.shape | |
| flat = value.reshape(-1, shape[-1]).contiguous() | |
| if value.dtype == torch.bfloat16: | |
| return gemma_rmsnorm(flat, weight, eps).reshape(shape) | |
| if value.dtype != torch.float32: | |
| raise ValueError("Expected BF16 states or FP32 residual sums") | |
| high, low = _bf16_pair_sum(flat) | |
| gemma_fused_add_rmsnorm(low, high, weight, eps) | |
| return low.reshape(shape) | |