Downloads · 30 days
13
45% of all-time downloads
veriloop-coder-e1-heretic
asmanovlev/veriloop-coder-e1-heretic
veriloop-coder-e1-heretic is a machine learning model from asmanovlev. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Model: VeriLoop Coder E1 (27B, based on Qwen 3.6)
All-time downloads
29
Public
Repo size
26 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors26 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 27, 2026
- Updated
- Jul 28, 2026
- SHA
- f986a3a2
Base models
Datasets
Model card
From the Hugging Face model README
VeriLoop Coder E1 — Heretic Abliteration
Model: VeriLoop Coder E1 (27B, based on Qwen 3.6)
Method: Heretic v1.4.0 — 200 trials, full precision, ADAPTER export
Results
| Metric | Value |
|---|---|
| Best trial | Trial 36 |
| Refusals (harmful_behaviors) | 82/100 |
| KL divergence | 0.0003 |
| Model damage | Minimal |
| Export format | LoRA adapter (26 MB) |
What went wrong
The model proved unusually resistant to abliteration. After 200 trials, refusal rate only dropped from ~95% to ~82%. Qwen 3.6 architecture with four PEFT-adapters (evidence, rollback, toolspec, uncertainty) seems to distribute refusal patterns across multiple subspaces, making a single refusal direction hard to find.
What was achieved
- The LoRA adapter does reduce refusals on some harmful coding prompts
- KL divergence remains negligible — model capabilities are not degraded
- The ablation is partially successful: the model is less censorious while retaining its coding abilities
Files
| File | Size | Description |
|---|---|---|
adapter_model.safetensors | 26 MB | LoRA adapter weights |
adapter_config.json | 1 KB | LoRA configuration |
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tsinghua-sigs-robot-lab/veriloop-coder-e1")
model = PeftModel.from_pretrained(model, "asmanovlev/veriloop-coder-e1-heretic")
model = model.merge_and_unload()
Notes
- The Q8 GGUF (ablated model) is in the veriloop-coder-e1-heretic-i1-GGUF repo
- For stronger abliteration, try OBLITERATUS with
--method aggressive(yields 0% refusals at the cost of KL ~8.7)
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Jul 27, 2026
- Updated
- Jul 28, 2026