Downloads · 30 days
6
18% of all-time downloads
llama400m-wikitext2-dora-adapter
leonzc/llama400m-wikitext2-dora-adapter
llama400m-wikitext2-dora-adapter is a machine learning model from leonzc. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Adapter only for DoRA fine-tuned LLaMA 400M model on Wikitext-2 using LMFlow This is the DoRA adapter for leonzc/llama400m-wikitext2-merged.
All-time downloads
34
Public
Repo size
276 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors356 MB · 77%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 29, 2025
- Updated
- Jul 29, 2025
- SHA
- 365c2740
Base models
Model card
From the Hugging Face model README
llama400m-wikitext2-dora-adapter
Adapter only for DoRA fine-tuned LLaMA 400M model on Wikitext-2 using LMFlow
Adapter Details
This is the DoRA adapter for leonzc/llama400m-wikitext2-merged.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load the base model first
base_model = AutoModelForCausalLM.from_pretrained("data4elm/Llama-400M-12L")
# Load the DoRA adapter
model = PeftModel.from_pretrained(base_model, "leonzc/llama400m-wikitext2-dora-adapter")
# Load the tokenizer from the base model
tokenizer = AutoTokenizer.from_pretrained("data4elm/Llama-400M-12L")
# Example usage
input_text = "What is the capital of France?"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(inputs.input_ids, max_length=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Jul 29, 2025
- Updated
- Jul 29, 2025