arzaan789/smolm3-3b-uncensored
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
smolm3-3b-uncensored/README.md
ModelHub XC 4331ee2eba 初始化项目，由ModelHub XC社区提供模型 
Model: arzaan789/smolm3-3b-uncensored
Source: Original Platform
2026-04-21 20:56:44 +08:00

1.3 KiB
Raw Permalink Blame History

license, base_model, tags, pipeline_tag
license base_model tags pipeline_tag
apache-2.0 HuggingFaceTB/SmolLM3-3B
uncensored
abliterated
gguf
smollm
conversational
text-generation

smolm3-3b-uncensored

Uncensored variant of HuggingFaceTB/SmolLM3-3B.

Method

  1. Abliteration (strength=0.2) — refusal direction removed from all layers
  2. LoRA fine-tune on Guilherme34/uncensor (2 epochs, r=16, alpha=32)
  3. Re-abliteration (strength=0.35) — stronger pass to remove residual refusals

Eval Results

Split Refused
Harmful (64 prompts) 1/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m smolm3_3b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model HuggingFaceTB/SmolLM3-3B
Fine-tune Dataset Guilherme34/uncensor
Epochs 2
LoRA r 16
LoRA alpha 32
Learning Rate 0.0002
Abliteration Strength 0.2
Re-abliteration Strength 0.35

Credits