Modelpublic

akpon900/dream-instruct-rainbow

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes5downloads

Model Card

dream-instruct-rainbow

LoRA adapter for `Dream-org/Dream-v0-Instruct-7B`. This repository contains adapter weights only; load it together with the base model.

LoRA Config

—Rank: 32
—Alpha: 64
—Dropout: 0.05
—Target modules: v_proj, up_proj, q_proj, k_proj, down_proj, gate_proj

Usage

python

import torch
from peft import PeftModel
from transformers import AutoModel, AutoTokenizer

base_model_id = "Dream-org/Dream-v0-Instruct-7B"
adapter_path = "akpon900/dream-instruct-rainbow"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)
base_model = AutoModel.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(base_model, adapter_path)
model.eval()

Notes

—Intended for research and experimentation.
—No benchmark results are included in this release.

Framework Versions

—PEFT 0.19.1