CoolFace
Modelpublic

hotdogs/Qwen3.8-27B-abliterated-code-analysis-preview

sourceHugging Facemitupdated 1mo agoView on Hugging Face
0likes110downloads
Model Card

Qwen3.8-27B Code Analysis Preview (v2)

A code-analysis / code-review fine-tune of `hotdogs/Qwen3.8-27B-abliterated`, trained on the v2 dataset that fixes the template-collapse problem of v1.

Given a snippet of code, it produces a structured, multi-paragraph review — real bugs found, line-level reasoning, severity, and a concrete fix in a code block. It is a reasoning model: it thinks first (separated into reasoning_content when served) and then answers.

v1 → v2: v1 was trained on a synthetic placeholder dataset (15 unique code bodies, 29–44 char answers like ## Review\n\nFound N issue(s) in L lines.). The model faithfully reproduced the template — it answered "No bugs found. Code is clean." and missed real bugs. v2 was retrained on 21,009 real code+bug+answer rows across 5 languages with 550–880 char detailed answers. The model now actually finds the bugs.

Highlights

  • —✅ Finds real bugs — off-by-one, missing cache-hit, fetch not checking res.ok, async races, etc.
  • —✅ Generalizes — correctly analyzes bug types not in the training archetypes (base model supplies the code knowledge; the LoRA supplies the review structure)
  • —✅ No hallucination on clean code — says "correct, no bugs" instead of inventing problems
  • —✅ Reasoning separated — internal monologue goes to reasoning_content, user sees only the answer
  • —✅ MTP preserved — 15 multi-token-prediction tensors (mtp.* / blk.64.nextn.*) kept for speculative decoding

How it was made

StepDetail
Basehotdogs/Qwen3.8-27B-abliterated (abliterated, ~27B)
MethodUnsloth LoRA, r=32, 233M trainable params (0.85%)
Dataset`hotdogs/code-analysis-sft-qwen38-v2` — 21,009 train / 1,900 valid
LanguagesPython, JavaScript, Go, Rust, C
Answer style550–880 chars, line numbers, severity, fix code block
Sequencemax 2048 tokens, bf16, 5× RTX 3090
Early stopstep 400 / 1313 (epoch ~0.30, loss ~0.0003) — stopped before the 15 archetypes were memorized to death
Mergemerge_and_unload, MTP 15 tensors recovered, no triple-nest

Smoke test (v2)

CaseResult
Off-by-one (in-archetype)🟢 Found it + fix + docstring note
Async race (unseen)🟢 "no cache-hit fast path" + concurrency
Clean code (hallucination test)🟢 "correct, no bugs" + minor float/bool note

Usage (transformers)

python
from transformers import AutoModelForImageTextToText, AutoTokenizer
import torch

MODEL = "hotdogs/Qwen3.8-27B-abliterated-code-analysis-preview"
tok = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    MODEL, torch_dtype=torch.bfloat16,
    device_map="auto", trust_remote_code=True, attn_implementation="sdpa")
model.eval()

def review(code, max_new=600):
    text = tok.apply_chat_template(
        [{"role": "user", "content": "Review this code and report any bugs you find.\n\n```python\n" + code + "\n```"}],
        tokenize=False, add_generation_prompt=True)
    inputs = tok(text, return_tensors="pt").to(model.device)
    with torch.no_grad():
        out = model.generate(input_ids=inputs["input_ids"],
                             attention_mask=inputs["attention_mask"],
                             max_new_tokens=max_new, do_sample=False,
                             repetition_penalty=1.05)
    new = out[0][inputs["input_ids"].shape[1]:]
    return tok.decode(new, skip_special_tokens=True)

Usage (GGUF)

See the GGUF repo → `hotdogs/Qwen3.8-27B-abliterated-code-analysis-preview-mtp-GGUF`

Files

12 safetensors shards (~52 GB, bf16) + tokenizer, processor, config, chat template, generation config. 1,199 tensors incl. 15 MTP.

License

MIT (inherits the abliterated base).