Instructions to use HuggingFaceBio/Carbon-X with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceBio/Carbon-X with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceBio/Carbon-X")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceBio/Carbon-X")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceBio/Carbon-X", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceBio/Carbon-X with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceBio/Carbon-X"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceBio/Carbon-X",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceBio/Carbon-X

SGLang

How to use HuggingFaceBio/Carbon-X 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 "HuggingFaceBio/Carbon-X" \
    --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": "HuggingFaceBio/Carbon-X",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "HuggingFaceBio/Carbon-X" \
        --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": "HuggingFaceBio/Carbon-X",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceBio/Carbon-X with Docker Model Runner:
```
docker model run hf.co/HuggingFaceBio/Carbon-X
```

Model card: how to use Carbon-X as a tool for an agent

by danaaubakirova HF Staff - opened 1 day ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+23

-50

initial commita1f607a0

Add Carbon-X weights (Carbon-14B-AGRPO v27.00-step-000000210) and model card0944a7cc

Name Qwen3-14B as the base model and drop the Clip-Higher paper link3f932345

danaaubakirova

Hugging Face Biology Research org 1 day ago

•

edited 1 day ago

Adds a Using Carbon-X as a tool for an agent section to the model card, placed before Limitations (and in the table of contents). It shows a short ask_carbon function that calls a Carbon-X vLLM server, links to ready-to-run examples, and lists tips for agent use.

New files:

examples/agent_tool.py: an OpenAI-style tool that passes DNA by reference, plus a minimal agent loop, for any chat model with tool calling.
examples/inspect_agent.py: an Inspect @tool and react() agent, with each sample's DNA kept in metadata.
skills/carbon-dna/: a skill for Claude Code and Codex CLI. SKILL.md plus a standard-library script with ask (a question about named DNA files) and compare (rank equal-length variants by sequence likelihood), configured with CARBON_BASE_URL.

Model card: how to use Carbon-X as a tool for an agentdbe3aafb

Move the agent-tool subsection to the end of How to use3913bc7e

Move the agent-tool section to the end of the model card83295b15

danaaubakirova changed pull request status to merged 1 day ago

Add an Inspect @tool example and the carbon-dna skill for coding agents687fa230

Move the agent-tool section before Limitations; link example files instead of inlining them3130db22

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment