Commit
•
5326551
1
Parent(s):
3987d0e
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,9 @@ tags:
|
|
| 13 |
- codeqwen
|
| 14 |
---
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
# YaRN 128K. 32K non extended GGUF here: [link](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-GGUF)
|
| 17 |
|
| 18 |
# Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
|
|
|
|
| 13 |
- codeqwen
|
| 14 |
---
|
| 15 |
|
| 16 |
+
> [!NOTE]
|
| 17 |
+
> Use 4bit quants (Q4_K_M) and above for 3B - lower quants will degrade accuracy
|
| 18 |
+
|
| 19 |
# YaRN 128K. 32K non extended GGUF here: [link](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-GGUF)
|
| 20 |
|
| 21 |
# Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
|