Mistral 7B Dockerfile Expert

Published by @container_craft · Community adapter

Generates optimised multi-stage Dockerfiles and Compose files. Minimises layer count, uses build cache correctly, and applies non-root user best practices.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base, "modelforgelab/mistral-7b-dockerfile-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.38
• vLLM