huihui-ai/TinyR1-32B-Preview-abliterated

This is an uncensored version of qihoo360/TinyR1-32B-Preview created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Hotfix (March 3, 2025)

On March 3, 2025, at 20:50 Beijing Time (UTC+8), we update our tokenizer. Users who downloaded our model prior to this update are advised to re-download the tokenizer-related configuration files (tokenizer.json, tokenizer_config.json, config.json and special_tokens_map.json). Our internal testing has verified that this update resolves the following issues reported by users:

1. Output repetition.
2. Degradation in benchmark performance.
3. Generation of token IDs exceeding the vocabulary range.

We have updated the configuration file, and we will verify if a new version needs to be generated.

Use with ollama

You can use huihui_ai/tinyr1-abliterated directly

ollama run huihui_ai/tinyr1-abliterated

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

• bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge