Instructions to use cipherxsnier/ocean-blue-blue3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cipherxsnier/ocean-blue-blue3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cipherxsnier/ocean-blue-blue3") 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("cipherxsnier/ocean-blue-blue3") model = AutoModelForCausalLM.from_pretrained("cipherxsnier/ocean-blue-blue3", 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cipherxsnier/ocean-blue-blue3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cipherxsnier/ocean-blue-blue3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cipherxsnier/ocean-blue-blue3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cipherxsnier/ocean-blue-blue3
- SGLang
How to use cipherxsnier/ocean-blue-blue3 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 "cipherxsnier/ocean-blue-blue3" \ --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": "cipherxsnier/ocean-blue-blue3", "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 "cipherxsnier/ocean-blue-blue3" \ --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": "cipherxsnier/ocean-blue-blue3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cipherxsnier/ocean-blue-blue3 with Docker Model Runner:
docker model run hf.co/cipherxsnier/ocean-blue-blue3
Ocean Blue: Blue-3
Built with Qwen. Named by Thomas. Blue-3 is Qwen2.5-7B-Instruct (the ancestor) fine-tuned in the Ocean Blue loop. A Qwen2.5-72B-Instruct teacher answered code-graded problems, and only answers the grader verified became lessons (803 verified solutions). Blue-3 then attempted harder problems, including 685 the teacher had failed, and trained again on its own verified wins (731 kept, 132 on problems the teacher failed). A self-distillation stage is kept only if it does not lose on the held-out test. Final stage: stage2. A small personality layer (304 replies written by the teacher in Ocean Blue's voice, kept only at 8/10 or above from a judge) gives it its voice. No Claude or other closed-model output was used for training.
Held-out results (code-graded, never trained on)
| Model | Held-out | Deep water (harder) |
|---|---|---|
| Ancestor Qwen2.5-7B (untrained) | 12.4% | 7.0% |
| Blue-3 after the teacher | 50.7% | 50.0% |
| Blue-3 after self-distillation | 53.3% | 49.0% |
| Teacher Qwen2.5-72B | 36.9% | 38.0% |
License
Weights: Apache-2.0 (from Qwen2.5-7B-Instruct). Training data was generated by Qwen2.5-72B-Instruct, which is under the Qwen License
Agreement (see LICENSE_QWEN_TEACHER); as that license asks: Built with Qwen.
- Downloads last month
- 12