Instructions to use safe049/Ruozhiba_llama3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use safe049/Ruozhiba_llama3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="safe049/Ruozhiba_llama3") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("safe049/Ruozhiba_llama3") model = AutoModelForCausalLM.from_pretrained("safe049/Ruozhiba_llama3", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use safe049/Ruozhiba_llama3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "safe049/Ruozhiba_llama3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "safe049/Ruozhiba_llama3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/safe049/Ruozhiba_llama3
- SGLang
How to use safe049/Ruozhiba_llama3 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 "safe049/Ruozhiba_llama3" \ --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": "safe049/Ruozhiba_llama3", "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 "safe049/Ruozhiba_llama3" \ --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": "safe049/Ruozhiba_llama3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use safe049/Ruozhiba_llama3 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for safe049/Ruozhiba_llama3 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for safe049/Ruozhiba_llama3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for safe049/Ruozhiba_llama3 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="safe049/Ruozhiba_llama3", max_seq_length=2048, ) - Docker Model Runner
How to use safe049/Ruozhiba_llama3 with Docker Model Runner:
docker model run hf.co/safe049/Ruozhiba_llama3
License Compatibility
Hi , I’d like to report a potential license incompatibility insafe049/Ruozhiba_llama3. I noticed that this fintuned model was derived from Undi95/Llama-3-LewdPlay-8B ,
which is licensed under CC-BY-NC 4.0 — a non-commercial license.
Meanwhile, the downstream model is published under the LLaMA 3 Community License, which permits commercial use (within Meta’s framework) and is considerably more permissive.
⚠️ Key License Conflicts:
CC-BY-NC 4.0 (Upstream):
• Prohibits all commercial use
• Requires attribution
• Must not be sublicensed under more permissive terms
LLaMA 3 Community License (Downstream):
• Allows commercial use under certain conditions
• Grants redistribution under the same license
• Does not enforce upstream non-commercial use restrictions
Conflict:
→ CC-BY-NC-licensed content must not be reused in ways that enable commercial applications
→ LLaMA 3’s permissive redistribution and commercial clauses contradict the upstream NC restriction
→ Downstream users may mistakenly believe they have more freedom than the upstream license permits
🔹 Suggestions for Resolving
1. To align with CC-BY-NC 4.0 and LLaMA 3 license obligations:
• Add a clear attribution in the model card specifying that this is derived from Undi95/Llama-3-LewdPlay-8B under CC-BY-NC 4.0
• Add a "NOTICE" or disclaimer noting that:
“This model includes material under CC-BY-NC 4.0 and is subject to non-commercial restrictions.”
• Consider removing the LLaMA 3 license label, or replacing it with a dual-license notice stating that:
Commercial use of this model is not allowed due to upstream CC-BY-NC components
2. Alternatively, relicense the model under CC-BY-NC 4.0, to comply with the upstream’s most restrictive terms.
Let me know if I misunderstood anything — happy to help clarify further!
Thanks for your attention!
Looking forward to your response!