Modelpublic

Suryanshg/Classification-DoD-translator

sourceHugging Facellama3.1updated 2mo agoView on Hugging Face

0likes14downloads

Model Card

Soft-to-Hard Prompt Translator

LoRA adapter that translates soft prompt embeddings into natural-language task instructions. Part of the "Learning to Translate from Soft to Hard LLM Prompts" project.

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-8B-Instruct", torch_dtype="auto", device_map="auto",
)
model = PeftModel.from_pretrained(base_model, "<path-to-adapter>")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")

Training Details

Parameter	Value
Base model	`meta-llama/Llama-3.1-8B-Instruct`
LoRA rank	4
LoRA alpha	8
Dropout	0.1
Target modules	downproj, gateproj, kproj, upproj, vproj, oproj, q_proj
PEFT version	0.18.0

License & Attribution

Built with Llama.