qwen-3.6-35b-a3b-teacher API & Inference Endpoint

Training data

Self-distillation on the base model's own rollouts. Qwen3.6-35B-A3B was sampled on SWE-smith task instances, each trajectory was graded by the SWE-smith harness, and the surviving set was curated as follows:

Correct only — the trajectory resolves its instance under recovered grading.
No cheating — trajectories whose assistant turns match a cheat-pattern regex are dropped.
No easy instances — instances solved by more than 75% of attempts (with at least 4 attempts) are dropped entirely, so the model does not spend its budget on problems it already solves.
Top-3 shortest per instance — among the correct trajectories for a base instance, keep the three with the fewest tokens, which favors direct solutions over meandering ones.
≤ 32,768 tokens.

The result is 14,268 training trajectories.

Training

Full-parameter bf16 SFT, one epoch:

Table

Steps	223 (1 epoch)
Batch size	64 sequences
Sequence length	32,768
Learning rate	6e-6, cosine, 5% warmup
Optimizer	FusedAdam (Transformer Engine), β = (0.9, 0.95), weight decay 0.0
Gradient clipping	1.0
Seed	1234
Hardware	8 × B200
Stack	verl + NeMo-Automodel, FSDP2 with expert parallelism 8

Usage

Serve it as you would the base model. Two things differ:

Use the bundled chat_template.jinja. It emits plain <|im_start|>role\ncontent<|im_end|> turns with no <think>/</think> injection, which is what the training trajectories look like.
Thinking is off. The trajectories were generated with enable_thinking=False, and the model was fine-tuned on them in that form.

Weights are bf16. Our own trajectory generation runs it under vLLM with online FP8 quantization.

License

Apache 2.0, inherited from the base model.

Training data

Correct only — the trajectory resolves its instance under recovered grading.
No cheating — trajectories whose assistant turns match a cheat-pattern regex are dropped.
No easy instances — instances solved by more than 75% of attempts (with at least 4 attempts) are dropped entirely, so the model does not spend its budget on problems it already solves.
Top-3 shortest per instance — among the correct trajectories for a base instance, keep the three with the fewest tokens, which favors direct solutions over meandering ones.
≤ 32,768 tokens.

The result is 14,268 training trajectories.

Training

Full-parameter bf16 SFT, one epoch:

Table

Steps	223 (1 epoch)
Batch size	64 sequences
Sequence length	32,768
Learning rate	6e-6, cosine, 5% warmup
Optimizer	FusedAdam (Transformer Engine), β = (0.9, 0.95), weight decay 0.0
Gradient clipping	1.0
Seed	1234
Hardware	8 × B200
Stack	verl + NeMo-Automodel, FSDP2 with expert parallelism 8

Usage

Serve it as you would the base model. Two things differ:

Use the bundled chat_template.jinja. It emits plain <|im_start|>role\ncontent<|im_end|> turns with no <think>/</think> injection, which is what the training trajectories look like.
Thinking is off. The trajectories were generated with enable_thinking=False, and the model was fine-tuned on them in that form.

Weights are bf16. Our own trajectory generation runs it under vLLM with online FP8 quantization.

License

Apache 2.0, inherited from the base model.

qwen-3.6-35b-a3b-teacher

README

Training data

Training

Usage

License

Explore FriendliAI today

README

Training data

Training

Usage

License