Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,11 @@ I simply converted it to MLX format with a quantization of 4-bit for better perf
|
|
| 27 |
# Notes:
|
| 28 |
- Seems to brush over the "thinking" process and immediately start answering, leading to extremely quick but correct answers.
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
# Alejandroolmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-4bit-mlx
|
| 32 |
|
|
|
|
| 27 |
# Notes:
|
| 28 |
- Seems to brush over the "thinking" process and immediately start answering, leading to extremely quick but correct answers.
|
| 29 |
|
| 30 |
+
## Other Types:
|
| 31 |
+
| Link | Type | Size| Notes |
|
| 32 |
+
|-------|-----------|-----------|-----------|
|
| 33 |
+
| [MLX] (https://huggingface.co/Alejandroolmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-8bit-mlx) | 8-bit | 8.10 GB | **Best Quality** |
|
| 34 |
+
| [MLX] (https://huggingface.co/Alejandroolmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-4bit-mlx) | 4-bit | 4.30 GB | Good Quality|
|
| 35 |
|
| 36 |
# Alejandroolmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-4bit-mlx
|
| 37 |
|