30 lines
1.1 KiB
Markdown
30 lines
1.1 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
quantized_by: stillerman
|
|
tags:
|
|
- llamafile
|
|
- gguf
|
|
|
|
language:
|
|
- en
|
|
datasets:
|
|
- HuggingFaceTB/smollm-corpus
|
|
---
|
|
|
|
# SmolLM-360M-Instruct - llamafile
|
|
|
|
This repo contains `.gguf` and `.llamafile` files for [SmolLM-360M-Instruct](https://huggingface.co/collections/HuggingFaceTB/smollm-6695016cad7167254ce15966). [Llamafiles](https://llamafile.ai/) are single-file executables (called a "llamafile") that run locally on most computers, with no installation.
|
|
|
|
# Use it in 3 lines!
|
|
```
|
|
wget https://huggingface.co/stillerman/SmolLM-360M-Instruct-Llamafile/resolve/main/SmolLM-360M-Instruct-F16.llamafile
|
|
chmod a+x SmolLM-360M-Instruct-F16.llamafile
|
|
./SmolLM-360M-Instruct-F16.llamafile
|
|
```
|
|
|
|
# Thank you to
|
|
- Huggingface for [SmolLM model family](https://huggingface.co/collections/HuggingFaceTB/smollm-6695016cad7167254ce15966)
|
|
- Mozilla for [Llamafile](https://llamafile.ai/)
|
|
- [llama.cpp](https://github.com/ggerganov/llama.cpp/)
|
|
- [Justine Tunney](https://huggingface.co/jartine) and [Compilade](https://github.com/compilade) for help |