metadata
datasets:
- zed-industries/zeta
license: apache-2.0
base_model: zed-industries/zeta
tags:
- mlx
About:
Tuned from Qwen2.5 coder for coding tasks
- Its a fine-tuned version of Qwen2.5-Coder-7B to support edit prediction in Zed. Fine-tuned using zeta dataset.
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:
https://huggingface.co/zed-industries/zeta (Base Model)
https://huggingface.co/lmstudio-community/zeta-GGUF (GGUF Version)
- 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).
- If looking for a larger mlx model, see the models below.
Other Types:
| Link | Type | Size | Notes |
|---|---|---|---|
| [MLX] (https://huggingface.co/AlejandroOlmedo/zeta-mlx) | Full | 15.2 GB | Best Quality |
| [MLX] (https://huggingface.co/AlejandroOlmedo/zeta-8bit-mlx) | 8-bit | 8.10 GB | Better Quality |
| [MLX] (https://huggingface.co/AlejandroOlmedo/zeta-4bit-mlx) | 4-bit | 4.30 GB | Good Quality |
AlejandroOlmedo/zeta-4bit-mlx
The Model AlejandroOlmedo/zeta-4bit-mlx was converted to MLX format from zed-industries/zeta using mlx-lm version 0.21.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("AlejandroOlmedo/zeta-4bit-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)