Instructions to use HuggingFaceBio/Carbon-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceBio/Carbon-3B with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceBio/Carbon-3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceBio/Carbon-3B")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceBio/Carbon-3B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceBio/Carbon-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceBio/Carbon-3B"
# 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-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceBio/Carbon-3B

SGLang

How to use HuggingFaceBio/Carbon-3B 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-3B" \
    --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-3B",
		"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-3B" \
        --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-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceBio/Carbon-3B with Docker Model Runner:
```
docker model run hf.co/HuggingFaceBio/Carbon-3B
```

Carbon-3B / tokenizer.py

Commit History

load chat_template in from_pretrained (vLLM apply_chat_template fix)

f2dd7fa
verified

kashif HF Staff commited on about 18 hours ago

fix convert_tokens_to_string byte-level detok (vLLM)

b232b2e
verified

kashif HF Staff commited on 2 days ago

tokenizer: expose .vocab property for fast-tokenizer-style callers (#4)

7fe1e11

kashif HF Staff commited on May 20

tokenizer: fix decode() to handle torch tensor input via .tolist()

ac0ca80
verified

kashif HF Staff commited on May 14

Update tokenizer.py

cac27f2
verified

GenerTeam commited on May 14

Fix tokenizer: EOS bug + decode skip_special_tokens=True empty string (#1)

f47e012

kashif HF Staff commited on May 13

Initial release · sourced from hf-carbon/carbon-3B-longctx-32k-from-mix2decay-429k @ step-453000

12de471
verified

loubnabnl HF Staff commited on May 12

Commit History

load chat_template in from_pretrained (vLLM apply_chat_template fix) f2dd7fa verified

fix convert_tokens_to_string byte-level detok (vLLM) b232b2e verified

tokenizer: expose .vocab property for fast-tokenizer-style callers (#4) 7fe1e11

tokenizer: fix decode() to handle torch tensor input via .tolist() ac0ca80 verified

Update tokenizer.py cac27f2 verified

Fix tokenizer: EOS bug + decode skip_special_tokens=True empty string (#1) f47e012

Initial release · sourced from hf-carbon/carbon-3B-longctx-32k-from-mix2decay-429k @ step-453000 12de471 verified