LASR-Callum

qwen3.6-27b-lora-1000ex-numina666-tulu334

README

License: apache-2.0

Mixture

Sized by example count, not by token budget.

Table with columns: Source, Examples, Tokens, % examples, % tokens, think block
Source	Examples	Tokens	% examples	% tokens	think block
NuminaMath-CoT	666	360,716	66.6%	68.1%	no think block
TULU3	167	115,516	16.7%	21.8%	empty `<think></think>`, excluded from loss
No Robots	167	53,461	16.7%	10.1%	empty `<think></think>`, excluded from loss
total	1000	529,693

Constitution: none.

Think blocks — three distinct states

Qwen3.6's chat template emits <think>\n\n</think> for any final assistant turn with no reasoning_content. Training a model to emit that marker is the documented reasoning-collapse pattern, so TULU3 and No Robots rows carry the marker as context but its tokens are excluded from the loss (mask_empty_think: true). NuminaMath rows carry no block at all; difficult-advice rows carry a real trace and are fully supervised.

Verified at token-ID level before launch: 0 rows leaked a user/system token into the loss, 0 empty-think markers carried loss, and no row with a real trace lost it.

What is supervised

Everything outside an assistant turn is -100. 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, 39 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 0.8028, mean token accuracy 0.7776, 529,693 tokens seen.

Table with columns: step, loss, token acc
step	loss	token acc
5	1.7039	0.6317
10	0.7780	0.8119
15	0.8537	0.7819
20	0.6970	0.8142
25	0.6834	0.8107
30	0.6616	0.8169

Status

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

Sibling arm: arm B.

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-numina666-tulu334")
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