Llama 3.1 70B Research Synthesis

Official adapter · maintained by LoRADock

Synthesizes technical research notes into evidence tables, disagreements, and prioritized open questions.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-70B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-70B-Instruct")
model = PeftModel.from_pretrained(base, "loradock/llama31-70b-research-synthesis")

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

• peft>=0.11
• transformers>=4.43
• vLLM