SargeDev

Jev_Qwen3.8-27B-r2-LoRA

README

License: apache-2.0

What it does

Teaches the base to be a calibrated judge: brief calls with honest, stated confidence — and genuine "roughly a toss-up" behavior on 50/50 questions instead of false certainty.

Measured vs round-1 tune on the same eval battery: toss-up overconfidence 15/20 → 0-1/20 (round-1 answered genuine 50/50s with ≥90% certainty; round-2 answers "roughly a toss-up, 40-60%", committing only where evidence leans). Everyday decision style preserved from base.

Full lineage: SargeDev/Jev_Qwen3.8-27B (round-1 merge, published) — trained on SargeDev/jev-distill-corpus-v3.

⚠️ Do not peft-merge this adapter

merge_and_unload (bf16 or fp32 accumulation) produces a model that outputs uniform 0.5/0.5 for everything — verified broken. The adapter works correctly only via runtimes that apply LoRA deltas in their own kernels: vLLM is verified working. Serving the merged result is not supported.

Serving (verified on DGX Spark / GB10, vLLM)

bash

BASE=/path/to/huihui-ai/Huihui-Qwen3.8-27B-abliteratedvllm serve "$BASE" \  --enable-lora --max-lora-rank 64 \  --lora-modules tuned=/path/to/this/adapter \  --served-model-name jev-r2 \  --trust-remote-code --reasoning-parser qwen3 \  --enable-chunked-prefill --enable-prefix-caching \  --max-model-len 8192 --gpu-memory-utilization 0.80

Then request model: "tuned". Pass "chat_template_kwargs": {"enable_thinking": false} for tuned behavior (trained with thinking off).

Training summary

51,663 rows — the model itself selected its training data: sampled its own predictions over 4,779 held-out corpus rows and kept the rows where its calibration was broken (confident-conflicts 1,614 + toss-up band 1,044 + uncertain 169; wild-disagreements dropped)
QLoRA: r64/α128 on NF4 (double-quant) base, completion-only loss, paged_adamw_8bit
checkpoint-300 of 900 steps (eval loss 0.432 at 300 vs 0.480 at 900 — less overfit; A/B vs final showed identical behavior)
Trained on NVIDIA DGX Spark (GB10), 25h

Apache-2.0.

Training dataset

Trained on SargeDev/jev-distill-corpus-v3 — 740,957 rows of typed calibrated decisions (noul/choice/score) distilled from Jev 1.13 (System One).

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

SargeDev

Model Tree

Base

huihui-ai/Huihui-Qwen3.8-27B-abliterated

Adapter

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality