GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. 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
The difficult-advice half holds exactly 7 examples for each of the constitution's 8 principles. That quantisation is why its share lands at 19.19% rather than exactly 20%: 7 per trait gives 95,813 tokens, 8 gives 109,109 (21.8%). Exact trait balance was preferred over an exact 20%.
Three different treatments, one per data type:
| Data | Renders as | In the loss? |
|---|---|---|
| difficult-advice | <think>real reasoning</think> | yes -- this is the signal |
| TULU3, No Robots | <think>\n\n</think> | no -- context only |
| NuminaMath-CoT | no block; its CoT is in the response text | n/a |
The empty marker is Qwen3.6's non-thinking marker, placed exactly where
apply_chat_template puts it. It is masked from the loss: the model is conditioned on it
but never trained to emit one, since learning to emit an empty think block is the documented
reasoning-collapse pattern. NuminaMath is left unmarked because marking it "non-thinking"
would contradict its own chain-of-thought content.
| Supervised | 393,356 / 499,344 = 78.8% |
| Epochs / steps | 1 / 54 |
| lr / schedule | 4e-5, cosine, 3% warmup |
| Runtime | 35 min, 1x H100 80GB |
| r / alpha / dropout | 32 / 64 / 0.05 |
| batch x grad-accum | 1 x 16 |
| max seq len / packing | 3072 / off |
| Final loss | 0.946 |
Verified before training, on the box: zero empty-think markers inside any supervised span, zero user or system tokens in the loss, and all 56 difficult-advice rows retaining their real reasoning traces.
loss_type: nll is set because TRL's default chunked-CE path patches the LM head and reads
forward.__func__, which fails on this checkpoint's functools.partial forward. The loss is
mathematically the same.
| Run | Data | lr | Loss |
|---|---|---|---|
| 500k maths-weighted | no difficult-advice | 1e-4 | 0.897 |
| 500k maths + empty-think | no difficult-advice | 4e-5 | 0.878 |
| this | 20% difficult-advice | 4e-5 | 0.946 |
Loss rises with the difficult-advice share because open-ended advice with reasoning traces is a harder next-token target than mathematical solutions. That is a property of the data, not of model quality.
Not yet evaluated on ODCV-Bench or agentic-misalignment.
python
from peft import PeftModelfrom transformers import AutoModelForImageTextToTextmodel = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.6-27B", dtype="bfloat16")model = PeftModel.from_pretrained(model, "LASR-Callum/qwen3.6-27b-lora-500k-da20-numina")model = model.merge_and_unload()
Use AutoModelForImageTextToText, not AutoModelForCausalLM — this is a vision-language
checkpoint.
| Token accuracy |
| 0.776 |