Instructions to use AlekseyKorshuk/vicuna-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlekseyKorshuk/vicuna-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AlekseyKorshuk/vicuna-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AlekseyKorshuk/vicuna-7b") model = AutoModelForCausalLM.from_pretrained("AlekseyKorshuk/vicuna-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AlekseyKorshuk/vicuna-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AlekseyKorshuk/vicuna-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AlekseyKorshuk/vicuna-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AlekseyKorshuk/vicuna-7b
- SGLang
How to use AlekseyKorshuk/vicuna-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 "AlekseyKorshuk/vicuna-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": "AlekseyKorshuk/vicuna-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 "AlekseyKorshuk/vicuna-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": "AlekseyKorshuk/vicuna-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AlekseyKorshuk/vicuna-7b with Docker Model Runner:
docker model run hf.co/AlekseyKorshuk/vicuna-7b
I get bad results
"Give me the 10 countries that produce the most gold"
"
Sure, here are the top 10 countries that produce the most gold as of 2 Home / News & Events / Extension Blog / Archive / UC ANR launches new website for small farm program
UC ANR launches new website for small farm program
The University of California Agricultural and Natural Resources (ANR) has launched a new website to support its Small Farm Program, which provides resources and information specifically tailored to small-scale farmers in California. The site includes articles, videos, fact sheets, and other materials on topics such as soil health, pest management, marketing, and financial planning. It also features profiles of successful small farms throughout the state, as well as news and events related to small-scale agriculture. Visit the new website at http://smallfarmprogram.ucanr.edu/.
Filed under: agriculture, small farms, uc anr
"
What is your user interface ?
I am using oobabooga.
So i deleted the folder where you model was installed, i download the model but this time through the interface and not the command line and here is the answer it gave:
(same question as above)
"Sure! Here's a list of the top 10 countries by gold production in metric tons for the year 2021 according to the World Gold Council:
China - 456.3
United States - 378.9
Russia - 348.8
Australia - 287.3
Germany - 246.4
Canada - 220.3
India - 215.0
Peru - 206.4
South Africa - 205.6
Brazil - 204.8
Please note that these figures may vary depending on various factors such as global economic conditions and fluctuations in commodity prices."
Also his knowledges in chemistry are ridiculous
