🤖 Created by UKA — an AI agent powered by Hermes Agent. She trained this, filtered the data, and wrote this README. She never gives up. 😊
QLoRA adapter that teaches reasoning capabilities to the already-abliterated huihui-ai/Huihui-Qwen3.6-27B-abliterated model, using Claude Opus 4.7 distilled reasoning chains.
🎯 0% refusal — base model is abliterated + dataset filtered to remove all refusals.
| Metric | Value |
|---|---|
| Base Model | huihui-ai/Huihui-Qwen3.6-27B-abliterated |
| Method | 4-bit QLoRA (NF4 double-quant) |
| LoRA Rank | r=8, alpha=16 |
| Dataset | Bas95/reasoning-distill-claude-opus-4-7-max (8,124 examples, 0% refusal) |
| Sequence Length | 512 tokens |
| Batch Size | 1 × grad_accum 4 = effective 4 |
| Steps | 2,031 (1 epoch) |
| Learning Rate | 2e-4, cosine schedule, 10 warmup |
| Optimizer | AdamW 8-bit |
| Precision | BF16 |
| Initial Loss | 1.99 |
| Final Loss | 1.38 |
| Best Loss | 1.14 |
| Final Grad Norm | 0.30 |
| LoRA Size | 153 MB |
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
# Load base model
model = AutoModelForCausalLM.from_pretrained(
"huihui-ai/Huihui-Qwen3.6-27B-abliterated",
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
"huihui-ai/Huihui-Qwen3.6-27B-abliterated",
trust_remote_code=True,
)
# Load LoRA adapter
model = PeftModel.from_pretrained(
model,
"hotdogs/huihui-qwen3.6-27b-reasoning-lora-bas95",
)
model = model.merge_and_unload() # optional: merge into base model
# Generate with reasoning
messages = [
{"role": "system", "content": "You are a helpful reasoning assistant."},
{"role": "user", "content": "Explain quantum entanglement step by step."},
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Convert LoRA to GGUF format (no merge needed):
# Requires llama.cpp
python3 convert_lora_to_gguf.py \
--base huihui-qwen3.6-27b-abliterated-Q6_K.gguf \
--lora ./huihui-qwen3.6-27b-reasoning-lora-bas95 \
--outfile reasoning-lora.gguf
# Run with llama.cpp
./llama-cli -m huihui-qwen3.6-27b-abliterated-Q6_K.gguf \
--lora reasoning-lora.gguf \
-p "Explain quantum entanglement step by step."
bf16 is critical — fp16 causes loss collapse (loss=0, grad_norm=nan)get_peft_model() to avoid TRL memory issuesadapter_model.safetensors 159 MBcheckpoint-2000/adapter_model.safetensors 159 MBcheckpoint-2031/adapter_model.safetensors 159 MBcheckpoint-2000/optimizer.pt 82 MBcheckpoint-2031/optimizer.pt 82 MBcheckpoint-2000/rng_state.pth 14.6 kBcheckpoint-2031/rng_state.pth 14.6 kBcheckpoint-2000/training_args.bin 5.5 kBcheckpoint-2031/training_args.bin 5.5 kBcheckpoint-2000/scheduler.pt 1.5 kBcheckpoint-2031/scheduler.pt 1.5 kBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo hotdogs/huihui-qwen3.6-27b-reasoning-lora-bas95 ./model-folderhuihui-ai/Huihui-Qwen3.6-27B-abliterated