Instructions to use Delta-Vector/Rei-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Delta-Vector/Rei-12B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Delta-Vector/Rei-12B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Rei-12B") model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Rei-12B") 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Delta-Vector/Rei-12B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Delta-Vector/Rei-12B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Delta-Vector/Rei-12B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Delta-Vector/Rei-12B
- SGLang
How to use Delta-Vector/Rei-12B 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 "Delta-Vector/Rei-12B" \ --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": "Delta-Vector/Rei-12B", "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 "Delta-Vector/Rei-12B" \ --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": "Delta-Vector/Rei-12B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Delta-Vector/Rei-12B with Docker Model Runner:
docker model run hf.co/Delta-Vector/Rei-12B
Very good model.
I think this model is great and is currently my favourite 12b. I can't complain much, it can handle a wide variety of personalities, scenarios. From modern to fantasy, it can even surprise you with jokes on occasion, It follows instructions very well, It seems to understand and be able to track clothes and character's position well, understands anatomy well enough, the model is smart. I like it a lot, it's great the way the model can understand what you are thinking or feeling more or less from subtleties.
The prose can range from beautiful and poetic, straightforward or even a pleasant mix. There might be a bit of a positivity bias and perhaps that can be improved, also ERP can be a bit bland or too horny at times, usually a few rerolls fix that apart from that I'm loving this model, first time in a while that I actually maxed out my admittedly limited 8k context.
Thanks for the review! Glad you enjoyed the model <3 - I'll try and fix on the issues haha.