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
```

Fix tokenizer persistence using merged source implementation

by edbeeching HF Staff - opened about 13 hours ago

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

+44

-97

edbeeching

Hugging Face Biology Research org about 13 hours ago

The custom tokenizer currently loses changes such as EOS <|im_end|> after saving and reloading. This copies tokenizer.py from the merged source tokenizer PR #9, commit b5d6e48f795d791388e712bde224f6d2668f9254.

The broader fix delegates standard metadata persistence to Transformers, preserves explicit caller overrides and AddedToken metadata, and saves DNA constructor settings. It retains DNA vocabulary-layout validation and standalone AutoTokenizer export. Legacy configuration fallbacks are removed.

Only tokenizer.py changes. The regression tests remain in the source tokenizer repository; model weights, tokenizer configuration, DNA encoding, and vocabulary IDs are unchanged.

Validation:

Source suite: 84 tests pass on Transformers 5.8.1 and 5.12.1.
Loaded this model's actual tokenizer configuration with the updated implementation and checked EOS/PAD, model length, padding side, AddedToken flags, chat template, DNA options, vocabulary IDs, and token masks through save/reload on Transformers 5.12.1.

Fix tokenizer persistence using merged source implementation746bbae2

edbeeching changed pull request status to merged about 13 hours ago

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