Downloads · 30 days
16
8% of all-time downloads
xlstm_pile_10m
PatrickHaller/xlstm_pile_10m
xlstm_pile_10m is a machine learning model from PatrickHaller. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
All-time downloads
195
Public
Parameters
1.2B
5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors5 GB · 100%
At a glance
- License
- mit
- Model type
- xlstm
- Access
- Public
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024
- SHA
- e6bb3d86
Model card
From the Hugging Face model README
An xLSTM Model
Trained with Helibrunna (fork)
To use this model the xLSTM package is required. We recommend to install it locally with conda:
git clone https://github.com/NX-AI/xlstm
cd xlstm
conda env create -n xlstm -f environment_pt220cu121.yaml
conda activate xlstm
Usage
from transformers import AutoModelForCasualLM, AutoTokenizer
model_name_or_path = "PatrickHaller/xlstm_dummy"
model = AutoModelForCasualLM.from_pretrained(model_name_or_path)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
input_ids = tokenizer.encode("Hello, my dog is cute", return_tensors="pt")
output = model.generate(input_ids, max_length=100, temperature=0.7, do_sample=True)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_text)
- Type
- xlstm
- License
- mit
- Languages
- en
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024