Commit
•
82606c2
1
Parent(s):
cb0cc2a
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
quantized_by: stillerman
|
| 5 |
+
tags:
|
| 6 |
+
- llamafile
|
| 7 |
+
- gguf
|
| 8 |
+
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
datasets:
|
| 12 |
+
- HuggingFaceTB/smollm-corpus
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# SmolLM-1.7B - llamafile
|
| 16 |
+
|
| 17 |
+
This repo contains `.gguf` and `.llamafile` files for [SmolLM-1.7B](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.
|
| 18 |
+
|
| 19 |
+
# Use it in 3 lines!
|
| 20 |
+
```
|
| 21 |
+
wget https://huggingface.co/stillerman/SmolLM-1.7B-Llamafile/resolve/main/SmolLM-1.7B-F16.llamafile
|
| 22 |
+
chmod a+x SmolLM-1.7B-F16.llamafile
|
| 23 |
+
./SmolLM-1.7B-F16.llamafile
|
| 24 |
+
```
|
| 25 |
+
|
| 26 |
+
# Thank you to
|
| 27 |
+
- Huggingface for [SmolLM model family](https://huggingface.co/collections/HuggingFaceTB/smollm-6695016cad7167254ce15966)
|
| 28 |
+
- Mozilla for [Llamafile](https://llamafile.ai/)
|
| 29 |
+
- [llama.cpp](https://github.com/ggerganov/llama.cpp/)
|
| 30 |
+
- [Justine Tunney](https://huggingface.co/jartine) and [Compilade](https://github.com/compilade) for help
|