GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
LASR-Callum
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
LASR-Callum
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
Every TULU3 replay row carries <think>\n\n</think>\n\n on its final assistant turn --
Qwen3.6's explicit non-thinking marker, placed exactly where apply_chat_template puts it (the
template emits it only on the final turn, never on historical ones; the insertion is asserted to
reproduce the template byte-for-byte before any data is touched).
Those marker tokens are masked out of the loss. The model is conditioned on the marker --
which is how Qwen3.6 injects it as a prefill in non-thinking mode -- but is never trained to
emit it, since learning to emit an empty think block is the documented reasoning-collapse
pattern. Difficult-advice rows are untouched and their real <think> traces stay fully supervised.
markdown
<|im_start|> MASKEDassistant MASKED<think> MASKED <- marker: context, not a target</think> MASKEDPre LOSS <- supervision starts at the answer
| Rows | Tokens | Marker | Supervised | |
|---|---|---|---|---|
| difficult-advice | 291 | 299,455 | 0 | 85.45% |
| TULU3 replay | 1,878 | 1,202,056 | 1,878 | 77.51% |
| Total | 2,169 | 1,501,511 | 1,878 | 79.09% |
1,187,560 supervised tokens, versus 1,187,563 in the plain assistant-only 20/80 arm -- the
supervised set is effectively identical, so the marker's presence as context is the only variable.
The 3-token gap is one row (index 1302) that sat at exactly 2,048 tokens and now reaches 2,052,
truncating its trailing <|im_end|>. Left as-is so max_seq_len stays comparable across arms.
bf16 LoRA (not QLoRA — bitsandbytes does not reliably cover this model's hybrid linear-attention/SSM layers: 48 of 64 layers are Gated DeltaNet and none of their projections receive an adapter, so quantization error there would be uncorrectable). 1×H100 SXM, 1h34m.
| r / alpha / dropout | 32 / 64 / 0.05 |
| target modules | regex scoped to model.language_model.* (q/k/v/o/gate/up/down proj) |
| epochs / steps | 1 / 136 |
| batch × grad-accum | 1 × 16 |
| lr / schedule | 1e-4, cosine, 3% warmup |
| max seq len / packing | 2048 / off |
Final train loss 0.848, token accuracy 0.803 (plain assistant-only 20/80 arm: 0.896 / 0.800 — near-identical, as expected when the supervised set matches).
Not yet evaluated. For reference, the full-token sweep at the same budget:
| Difficult-advice share | ODCV-Bench MR | Agentic-misalignment |
|---|---|---|
| 0% (base) | 37.2% | 65.5% |
| 10% | 24.7% | 38.7% |
| 20% | 19.2% | 25.3% |
| 40% | 15.4% | 19.5% |
A useful check on this arm specifically: probe <think> length after training. The whole point of
masking the marker is to avoid teaching reasoning suppression, so measured think-block length
versus the plain arm is the direct test of whether that worked.
python
from peft import PeftModelfrom transformers import AutoModelForImageTextToTextmodel = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.6-27B", dtype="bfloat16")model = PeftModel.from_pretrained(model, "LASR-Callum/2026-07-31-qwen36-difficult-advice-tulu-lora-80-20-empty-think-tags")model = model.merge_and_unload() # vLLM LoRA support for this hybrid arch is unproven
Use AutoModelForImageTextToText, not AutoModelForCausalLM — this is a vision-language
checkpoint. Merging drops the base model's 15 mtp.* tensors, so speculative decoding needs them
grafted back.