Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,13 @@ tags:
|
|
13 |
This is an uncensored version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
|
14 |
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Use with ollama
|
18 |
|
|
|
13 |
This is an uncensored version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
|
14 |
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
|
15 |
|
16 |
+
If "\<think\>" does not appear or refuses to respond, you can first provide an example to guide, and then ask your question.
|
17 |
+
For instance:
|
18 |
+
|
19 |
+
```
|
20 |
+
How many 'r' characters are there in the word "strawberry"?
|
21 |
+
```
|
22 |
+
|
23 |
|
24 |
## Use with ollama
|
25 |
|