Instructions to use Alsebay/SaoRPM-2x8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alsebay/SaoRPM-2x8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Alsebay/SaoRPM-2x8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Alsebay/SaoRPM-2x8B") model = AutoModelForCausalLM.from_pretrained("Alsebay/SaoRPM-2x8B", 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 Alsebay/SaoRPM-2x8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Alsebay/SaoRPM-2x8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Alsebay/SaoRPM-2x8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Alsebay/SaoRPM-2x8B
- SGLang
How to use Alsebay/SaoRPM-2x8B 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 "Alsebay/SaoRPM-2x8B" \ --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": "Alsebay/SaoRPM-2x8B", "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 "Alsebay/SaoRPM-2x8B" \ --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": "Alsebay/SaoRPM-2x8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Alsebay/SaoRPM-2x8B with Docker Model Runner:
docker model run hf.co/Alsebay/SaoRPM-2x8B
## 🚨License Conflict: LLaMA 3.2 vs CC BY-NC 4.0
Hi, I'd like to report a License Conflict in Alsebay/SaoRPM-2x8B. I noticed this model was fine-tuned from Sao10K/L3-8B-Lunaris-v1, which is released under the LLaMA 3.2 Community License. From what I can see, Alsebay/SaoRPM-2x8B is currently licensed under CC BY-NC 4.0, and also includes additional usage restrictions (e.g., ethics/privacy disclaimers and local law compliance statements). That may raise some compliance questions, because the META LLAMA 3 COMMUNITY LICENSE AGREEMENT has strict requirements for redistribution, naming, and licensing that may not be compatible with more restrictive downstream terms.
⚠️ Key violations of LLaMA 3 license terms:
Clause 1.b.i – Redistribution and Use:
• No license file included (should contain the META LLAMA 3 COMMUNITY LICENSE AGREEMENT)
• "Built with Meta Llama 3" is not prominently displayed
• Model name does not begin with “Llama 3”, which is required for any derivative
Clause 1.b.iii – Required Notice:
• Missing the following required text in a "NOTICE" file:
“Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
Clause 1.iv – Acceptable Use Policy:
• No mention of Meta’s Acceptable Use Policy, which must be passed on to downstream users
Clause 2 – Additional Commercial Terms:
• No clarification about the 700M MAU (monthly active users) threshold — making commercial usage ambiguous
Meanwhile, CC BY-NC 4.0 introduces:
• Prohibitions on commercial use (NC = NonCommercial)
• Additional human-authored restrictions (e.g., ethics/privacy statements)
• Potential limitations on redistribution based on jurisdiction
Using a more restrictive license like CC BY-NC 4.0 on top of a LLaMA 3.2–licensed base model might violate the original license’s requirement that derivatives must not impose incompatible or conflicting terms. This could confuse downstream users about:
• Whether redistribution is allowed
• Whether the model complies with Meta’s terms
• What usage is actually permitted (especially in research or startup settings)
🔹 Suggestions (just a friendly heads-up! 😊):
To help bring this in line with LLaMA 3.2’s licensing terms, it might be worth considering:
• Including a copy of the LLaMA 3.2 license
• Adding the required “NOTICE” file
• If the intention is to restrict commercial use, it may be better to stick with LLaMA 3.2 only, which already has provisions regarding acceptable use and commercial thresholds (like the 700M MAU clause)
Thanks for your attention!
Your reply would be much appreciated!