Instructions to use dphn/dolphin-llama2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dphn/dolphin-llama2-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dphn/dolphin-llama2-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dphn/dolphin-llama2-7b") model = AutoModelForCausalLM.from_pretrained("dphn/dolphin-llama2-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dphn/dolphin-llama2-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dphn/dolphin-llama2-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dphn/dolphin-llama2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dphn/dolphin-llama2-7b
- SGLang
How to use dphn/dolphin-llama2-7b 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 "dphn/dolphin-llama2-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dphn/dolphin-llama2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "dphn/dolphin-llama2-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dphn/dolphin-llama2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dphn/dolphin-llama2-7b with Docker Model Runner:
docker model run hf.co/dphn/dolphin-llama2-7b
Nice little one
I know this little one might not bring home all that many awards, but it just might be my favorite in this size group.
I made a minimal test character with it, half of the time she doesn't know what is she's talking about, but would still come out cute and charming despite being wrong.
She was very much against any kind of genocide, would refuse to help with any form of ethnic cleansing, but she would have no problem helping with any other kind of "chemistry projects". Perfectly balanced.
Dolphin dataset has potential. Maybe performance could be boosted a little bit by merging some of the prompts in datasets to have more longer examples, closer to max 4k tokens. Either case, thanks for all the great work.