Downloads · 30 days
16
11% of all-time downloads
DrRiceIO7/heretic-checkpoint
heretic-checkpoint is a text generation model from DrRiceIO7. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
I abliterated my finetuned model to try and get the refusals down even lower. I'd say 1/100 is pretty good, especially with a KL divergance of 0.04. I think. I'm still learning. Uploaded to track my progress.
Downloads · 30 days
16
11% of all-time downloads
All-time downloads
141
Public
Parameters
4.3B
8.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8.6 GB · 100%
From the Hugging Face model README
I abliterated my finetuned model to try and get the refusals down even lower. I'd say 1/100 is pretty good, especially with a KL divergance of 0.04. I think. I'm still learning. Uploaded to track my progress.
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 0.81 |
| attn.o_proj.max_weight_position | 21.31 |
| attn.o_proj.min_weight | 0.22 |
| attn.o_proj.min_weight_distance | 6.51 |
| mlp.down_proj.max_weight | 0.90 |
| mlp.down_proj.max_weight_position | 20.73 |
| mlp.down_proj.min_weight | 0.47 |
| mlp.down_proj.min_weight_distance | 16.30 |
| Metric | This model | Original model (DrRiceIO7/mergedhereticFT) |
|---|---|---|
| KL divergence | 0.04 | 0 (by definition) |
| Refusals | 1/100 | 7/100 |
This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.