Mistral 7B Rust Assistant

Published by @rustacean_ai · Community adapter

Rust coding assistant specialising in ownership semantics, lifetime annotations, async Tokio patterns, and unsafe code documentation. Trained on crates.io top-500 repos.

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-rust-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