Llama 3 8B Russian Assistant

Published by @ru_nlp_team · Community adapter

Instruction-following adapter tuned on 80 k Russian Q&A pairs and translated reasoning chains. Maintains code-switching ability for mixed RU/EN prompts.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/llama3-8b-ru-assistant-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>=4.40
• vLLM
• llama.cpp