Downloads · 30 days
0
ademyanchuk/tinyllama-quantized
tinyllama-quantized is a machine learning model from ademyanchuk. 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.
Quantiazied tinyllama model (stories15m.pt). See original repo: https://github.com/karpathy/llama2.c See how to quantize here: https://github.com/ademyanchuk/llama2.c/blob/master/export.pyL282C14-L282C14 Use version 3…
Downloads · 30 days
0
Access
Public
Updated Sep 27, 2023
Repo size
16.2 MB
Likes
0
Public
Click a slice to open those files.
.bin16.2 MB · 100%
From the Hugging Face model README
Quantiazied tinyllama model (stories15m.pt). See original repo: https://github.com/karpathy/llama2.c See how to quantize here: https://github.com/ademyanchuk/llama2.c/blob/master/export.py#L282C14-L282C14 Use version 3 of export on stories15m.pt model.
Use the model in this rust port of llama2.c project: https://github.com/ademyanchuk/llama2-rs