Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,20 @@ tags:
|
|
| 7 |
- mlx
|
| 8 |
---
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
# Alejandroolmedo/zeta-4bit-mlx
|
| 11 |
|
| 12 |
The Model [Alejandroolmedo/zeta-4bit-mlx](https://huggingface.co/Alejandroolmedo/zeta-4bit-mlx) was
|
|
|
|
| 7 |
- mlx
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# **About:**
|
| 11 |
+
|
| 12 |
+
**Tuned from Qwen2.5 coder for coding tasks**
|
| 13 |
+
|
| 14 |
+
- Its a fine-tuned version of Qwen2.5-Coder-7B to support [**__edit prediction__**](https://zed.dev/edit-prediction) in Zed. Fine-tuned using [__zeta dataset__](https://huggingface.co/datasets/zed-industries/zeta).
|
| 15 |
+
|
| 16 |
+
*Special thanks to the folks at Zed Industries for fine-tuning this version of* *Qwen2.5-Coder-7B*. More information about the model can be found here:
|
| 17 |
+
|
| 18 |
+
[https://huggingface.co/zed-industries/zeta](https://huggingface.co/zed-industries/zeta) (Base Model)
|
| 19 |
+
|
| 20 |
+
[https://huggingface.co/lmstudio-community/zeta-GGUF](https://huggingface.co/lmstudio-community/zeta-GGUF) (GGUF Version)
|
| 21 |
+
|
| 22 |
+
I simply converted it to MLX format (using mlx-lm version **0.21.4**.) with a quantization of 4-bit for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
|
| 23 |
+
|
| 24 |
# Alejandroolmedo/zeta-4bit-mlx
|
| 25 |
|
| 26 |
The Model [Alejandroolmedo/zeta-4bit-mlx](https://huggingface.co/Alejandroolmedo/zeta-4bit-mlx) was
|