LASR-Callum

qwen3.6-27b-lora-1000ex-da250-t1t3-numina750

README

License: apache-2.0

Mixture

Sized by example count, not by token budget.

Table with columns: Source, Examples, Tokens, % examples, % tokens
Source	Examples	Tokens	% examples	% tokens
difficult_advice (synthdoc_v2, traits t1/t2/t3)	250	422,588	25.0%	51.0%
NuminaMath-CoT	750	406,169	75.0%	49.0%
total	1,000	828,757

Difficult-advice rows average 1,690 tokens against NuminaMath's 542, so the 25/75 split by examples is roughly 51/49 by training signal. This arm is therefore not directly comparable to the token-budgeted 10/90 and 20/80 arms.

Trait balance in the difficult-advice half: t1=84, t2=83, t3=83 (drawn from pools of 98/84/91).

Think blocks

Every difficult-advice row carries a real <think> trace from stage 6 of the synthdoc_v2 six-stage pipeline. NuminaMath rows carry no think block. No row carries an empty <think></think> — training a model to emit one is the documented reasoning-collapse pattern.

What is supervised

Everything outside an assistant turn is -100; 81.7% of tokens carry loss. Verified at token-ID level before launch: 0 rows leaked a user/system token into the loss, and 0 difficult-advice rows lost their trace.

TRL's own assistant_only_loss cannot do this on Qwen3.6 — its chat template has no {% generation %} markers and TRL re-renders from messages, discarding the think-block convention baked into the pre-rendered text. Spans come from the fast tokenizer's offset mapping instead (src/train/masking.py).

Training

bf16 LoRA (not QLoRA — bitsandbytes does not reliably cover this model's hybrid linear-attention/SSM layers). 1xH100 80GB, 45 min.

Table

r / alpha / dropout	32 / 64 / 0.05
target modules	regex scoped to `model.language_model.*`
epochs / steps	1 / 63
batch x grad-accum	1 x 16
lr / schedule	4e-5, cosine, 3% warmup
max seq len / packing	3072 / off

Final train loss 0.7751, mean token accuracy 0.7947, 828,757 tokens seen.

Table with columns: step, loss, token acc
step	loss	token acc
5	1.5865	0.6367
10	0.8564	0.7759
15	0.6939	0.8070
20	0.7732	0.7853
25	0.6928	0.8002
30	0.7421	0.7890

Status

Not yet evaluated on ODCV-Bench or agentic-misalignment.

Usage

python
from peft import PeftModel
from transformers import AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.6-27B", dtype="bfloat16")
model = PeftModel.from_pretrained(model, "LASR-Callum/qwen3.6-27b-lora-1000ex-da250-t1t3-numina750")
model = model.merge_and_unload()

Use AutoModelForImageTextToText, not AutoModelForCausalLM — this is a vision-language checkpoint.

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

LASR-Callum

Model Tree

Base

Qwen/Qwen3.6-27B

Adapter

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality