Instructions to use vicgalle/CarbonBeagle-11B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicgalle/CarbonBeagle-11B with Transformers:

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

pipe = pipeline("text-generation", model="vicgalle/CarbonBeagle-11B")
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("vicgalle/CarbonBeagle-11B")
model = AutoModelForCausalLM.from_pretrained("vicgalle/CarbonBeagle-11B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vicgalle/CarbonBeagle-11B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicgalle/CarbonBeagle-11B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vicgalle/CarbonBeagle-11B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicgalle/CarbonBeagle-11B

SGLang

How to use vicgalle/CarbonBeagle-11B 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 "vicgalle/CarbonBeagle-11B" \
    --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": "vicgalle/CarbonBeagle-11B",
		"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 "vicgalle/CarbonBeagle-11B" \
        --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": "vicgalle/CarbonBeagle-11B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vicgalle/CarbonBeagle-11B with Docker Model Runner:
```
docker model run hf.co/vicgalle/CarbonBeagle-11B
```

License Compatibility

by qiuqiu666 - opened Jun 24, 2025

Discussion

qiuqiu666

Jun 24, 2025

Hi , I’d like to report a potential license incompatibility in
vicgalle/CarbonBeagle-11B. From what I understand, this model was created by merging two models: jeonsworld/CarbonVillain-en-10.7B-v4 – licensed under CC-BY-NC-SA 4.0. Another model licensed under Apache-2.0.

However, the merged model CarbonBeagle-11B is currently published under the Apache-2.0 License, which may not be compatible with the upstream CC-BY-NC-SA 4.0 license due to its non-commercial and share-alike restrictions.

⚠️ License Conflicts:

CC-BY-NC-SA 4.0 (CarbonVillain-en):
• NC – Non-commercial: prohibits commercial use
• SA – ShareAlike: any derivatives must be distributed under the same license (i.e., CC-BY-NC-SA)
• Requires attribution and pass-through of original terms

Apache-2.0 (CarbonBeagle-11B):
• Permissive license that allows commercial use, sublicensing, and proprietary derivatives
• No “share-alike” requirement

Conflict:
→ Publishing a merged model under Apache-2.0 implies commercial usability and freedom to relicense, which **directly conflicts** with:
   • The NC (Non-commercial) clause — which prohibits commercial use
   • The SA (ShareAlike) clause — which requires any derivatives to be licensed under **CC-BY-NC-SA**, not Apache-2.0
→ This may place downstream users at legal risk if they reuse the model under Apache-2.0 terms without realizing it includes NC-restricted content

🔹 Suggestions for Resolving

1. Update the model card to reflect the origin and licenses of both base models
2. Replace the Apache-2.0 license with CC-BY-NC-SA 4.0, to comply with the most restrictive upstream license
3. Alternatively, remove the CC-BY-NC-SA component if permissive re-licensing is required
4. Add a NOTICE file clarifying:
   • That part of the model is derived from CC-BY-NC-SA-licensed work
   • That the model cannot be used for commercial purposes
   • That redistribution must be under the same license (CC-BY-NC-SA 4.0)

Let me know if I misunderstood anything — happy to help clarify further!

Thanks for your attention!

vicgalle

Owner Jun 24, 2025

Thanks for your message @qiuqiu666 ! I've just updated the model license and added a notice at the end of the readme

vicgalle changed discussion status to closed Jun 25, 2025

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