Instructions to use kuleshov/llama-7b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kuleshov/llama-7b-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kuleshov/llama-7b-4bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kuleshov/llama-7b-4bit") model = AutoModelForCausalLM.from_pretrained("kuleshov/llama-7b-4bit") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kuleshov/llama-7b-4bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kuleshov/llama-7b-4bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kuleshov/llama-7b-4bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kuleshov/llama-7b-4bit
- SGLang
How to use kuleshov/llama-7b-4bit 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 "kuleshov/llama-7b-4bit" \ --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": "kuleshov/llama-7b-4bit", "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 "kuleshov/llama-7b-4bit" \ --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": "kuleshov/llama-7b-4bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kuleshov/llama-7b-4bit with Docker Model Runner:
docker model run hf.co/kuleshov/llama-7b-4bit
Adding `safetensors` variant of this model
#9 opened over 2 years ago
by
SFconvertbot
Adding `safetensors` variant of this model
#8 opened almost 3 years ago
by
SFconvertbot
Adding `safetensors` variant of this model
#7 opened almost 3 years ago
by
SFconvertbot
Can You Provide tokenizer
#6 opened almost 3 years ago
by
xavier666
🚩 Report : Ethical issue(s)
#5 opened about 3 years ago
by
PaopaoFace
inference example
👍 1
1
#4 opened about 3 years ago
by
rrkotik
all layer included?
#3 opened about 3 years ago
by
baby1
Finetunig the model
#2 opened about 3 years ago
by
zokica
Should it run on 8gb vram gpu?
2
#1 opened about 3 years ago
by
hlertarinto