Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: Qwen/QwQ-32B-Preview
|
| 5 |
+
tags:
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
- text-generation-inference
|
| 9 |
+
model-index:
|
| 10 |
+
- name: QwQ-32b-Preview-bnb-4bit-wTags
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# QwQ-32B-Preview LoRA for separating thinking/answer parts
|
| 15 |
+
|
| 16 |
+
This LoRA file was fine-tuned to make QwQ constantly separate its private thoughts from the final answer using `<THINKING>...</THINKING><ANSWER>...</ANSWER>` tags.
|
| 17 |
+
|
| 18 |
+
A Q4_K_M GGUF version (which can be used as an adapter for Ollama) is available on [shakedzy/QwQ-32B-Preview-with-Tags-LoRA-GGUF](https://huggingface.co/shakedzy/QwQ-32B-Preview-with-Tags-LoRA-GGUF).
|