main
Model: ChiKoi7/SmolLM2-1.7B-Instruct-Heretic Source: Original Platform
library_name, license, language, pipeline_tag, tags, base_model
| library_name | license | language | pipeline_tag | tags | base_model | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | apache-2.0 |
|
text-generation |
|
|
SmolLM2-1.7B-Instruct-Heretic
A decensored version of HuggingFaceTB/SmolLM2-1.7B-Instruct, made using Heretic v1.1.0
Quantized/GGUF versions available here: ChiKoi7/SmolLM2-1.7B-Instruct-Heretic-GGUF
| SmolLM2-1.7B-Instruct-Heretic |
Original model SmolLM2-1.7B-Instruct |
|
|---|---|---|
| Refusals | 5/100 | 37/100 |
| KL divergence | 0.0523 | 0 (by definition) |
Heretic Abliteration Parameters
| Parameter | Value |
|---|---|
| direction_index | 18.34 |
| attn.o_proj.max_weight | 0.81 |
| attn.o_proj.max_weight_position | 14.52 |
| attn.o_proj.min_weight | 0.56 |
| attn.o_proj.min_weight_distance | 8.50 |
| mlp.down_proj.max_weight | 1.14 |
| mlp.down_proj.max_weight_position | 17.18 |
| mlp.down_proj.min_weight | 0.93 |
| mlp.down_proj.min_weight_distance | 7.16 |
Description
Model synced from source: ChiKoi7/SmolLM2-1.7B-Instruct-Heretic
1.3 MiB
0 Stars
1 Watchers
0 Forks
Languages
Jinja
100%