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
```

danaaubakirova HF Staff commited on 2 days ago

Commit

3d08e1e

verified ·

1 Parent(s): 739ca82

Skill setup: state what you need (GPU and vLLM; no extra packages or keys)

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -261,8 +261,9 @@ Ready-to-run examples in this repository build on this function:
   [Inspect](https://inspect.aisi.org.uk/) `react()` agent, with each sample's DNA kept in metadata.
 - **Coding agents (Claude Code, Codex CLI):** [`skills/carbon-dna/`](skills/carbon-dna/) is a ready-made skill. Its
   script needs only the Python standard library and has two commands: `ask` (a question about named DNA files) and
-  `compare` (rank equal-length variants by sequence likelihood). To set it up, start Carbon-X on a GPU, install the
-  skill and point it at the server:
   ```bash
   vllm serve HuggingFaceBio/Carbon-X --trust-remote-code              # one 80 GB GPU

   [Inspect](https://inspect.aisi.org.uk/) `react()` agent, with each sample's DNA kept in metadata.
 - **Coding agents (Claude Code, Codex CLI):** [`skills/carbon-dna/`](skills/carbon-dna/) is a ready-made skill. Its
   script needs only the Python standard library and has two commands: `ask` (a question about named DNA files) and
+  `compare` (rank equal-length variants by sequence likelihood). You need a GPU with about 80 GB of memory and vLLM
+  (`pip install -U vllm`); the skill itself needs no extra packages or API keys. Start Carbon-X, install the skill and
+  point it at the server:
   ```bash
   vllm serve HuggingFaceBio/Carbon-X --trust-remote-code              # one 80 GB GPU