Instructions to use microsoft/Orca-2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/Orca-2-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/Orca-2-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/Orca-2-7b") model = AutoModelForCausalLM.from_pretrained("microsoft/Orca-2-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/Orca-2-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/Orca-2-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/Orca-2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/microsoft/Orca-2-7b
- SGLang
How to use microsoft/Orca-2-7b 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 "microsoft/Orca-2-7b" \ --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": "microsoft/Orca-2-7b", "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 "microsoft/Orca-2-7b" \ --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": "microsoft/Orca-2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use microsoft/Orca-2-7b with Docker Model Runner:
docker model run hf.co/microsoft/Orca-2-7b
Update README.md
#20 opened 4 months ago
by
ReactionControl
Adding `safetensors` variant of this model
#19 opened about 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#18 opened about 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#17 opened about 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#16 opened about 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#15 opened about 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#14 opened over 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#13 opened about 2 years ago
by
SFconvertbot
Adding Evaluation Results
#12 opened about 2 years ago
by
leaderboard-pr-bot
Error: The model type 'llama' is not recognized. Please check the model name.
#11 opened over 2 years ago
by
ayeshakhatunsujana
Might I know the learning rate in training phase of orca-2 models?
#10 opened over 2 years ago
by
atiyah
Orca may violate to OpenAI's Terms of Use
🤯 1
6
#9 opened over 2 years ago
by
icoxfog417
Finetuned model is less in size than original model
1
#8 opened over 2 years ago
by
hiiamsid
Data opensource?
👍 6
#6 opened over 2 years ago
by
zxs1997zju
Dataset release?
🔥👍 8
#5 opened over 2 years ago
by
SinanAkkoyun
Inference takes roughly 3 minutes on a 4090
4
#4 opened over 2 years ago
by
macadeliccc
Update README.md
#3 opened over 2 years ago
by
ameerazam08