Instructions to use HuggingFaceBio/Carbon-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceBio/Carbon-8B with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceBio/Carbon-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceBio/Carbon-8B")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceBio/Carbon-8B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceBio/Carbon-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceBio/Carbon-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceBio/Carbon-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceBio/Carbon-8B

SGLang

How to use HuggingFaceBio/Carbon-8B 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-8B" \
    --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": "HuggingFaceBio/Carbon-8B",
		"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 "HuggingFaceBio/Carbon-8B" \
        --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": "HuggingFaceBio/Carbon-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceBio/Carbon-8B with Docker Model Runner:
```
docker model run hf.co/HuggingFaceBio/Carbon-8B
```

Carbon-8B / tokenizer.py

Commit History

load chat_template in from_pretrained (vLLM apply_chat_template fix)

88914e7
verified

kashif HF Staff commited on about 13 hours ago

load chat_template in from_pretrained (vLLM apply_chat_template fix)

9d0177f
verified

kashif HF Staff commited on 1 day ago

fix convert_tokens_to_string byte-level detok (vLLM)

f5b2510
verified

kashif HF Staff commited on 3 days ago

tokenizer: expose .vocab property for fast-tokenizer-style callers (#1)

5b136ed

kashif HF Staff commited on May 20

tokenizer: sync with Carbon-500M/3B (warnings, add_special_tokens pass-through, tolist in decode)

578c911
verified

kashif HF Staff commited on May 19

Initial upload from HuggingFaceBio/carbon-8B-longctx-32k-from-1T-decay@step-227500 with new README

9cb7d0e
verified

loubnabnl HF Staff commited on May 17

Commit History

load chat_template in from_pretrained (vLLM apply_chat_template fix) 88914e7 verified

load chat_template in from_pretrained (vLLM apply_chat_template fix) 9d0177f verified

fix convert_tokens_to_string byte-level detok (vLLM) f5b2510 verified

tokenizer: expose .vocab property for fast-tokenizer-style callers (#1) 5b136ed

tokenizer: sync with Carbon-500M/3B (warnings, add_special_tokens pass-through, tolist in decode) 578c911 verified