ipfipfipf

Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29

README

License: apache-2.0

Training setup

Table

Base	`Qwen/Qwen3.5-9B`
Algorithm	GRPO + SDPO (self-skill-all, skill-KD `mode=both`, KD coef 0.01, `--no-sdpo-pure-distill`, `--sdpo-response-prefix skill`)
Domains	math, code, search — one mixed multitask stream
Rollouts	multi-turn native tool calling, up to 20 turns; thinking enabled
Max response length	16384 tokens (train and eval matched)
Steps	31 rollouts trained; this checkpoint is step 29

Held-out results

pass@1 / pass@8, greedy-free sampling, 16384-token response cap:

Table with columns: Benchmark, pass@1, pass@8
Benchmark	pass@1	pass@8
AIME 2024	84.2	96.7
AIME 2025	81.7	100.0
AMO-Bench	28.0	52.0
OJBench (medium, 77 problems)	31.8	59.7

AMO-Bench and OJBench are the best numbers we have on record for a 9B model in this line of work (previous best: AMO 22.7, OJBench 29.5).

Caveats worth knowing before you compare against these:

AIME 2024/2025 are saturated for this model — pass@8 reaches 100%, so they can no longer rank checkpoints. Our training curve uses AIME-2026 instead.
AMO-Bench pass@8 is depressed by truncation, not by reasoning failure: the median sample sits exactly at the 16384-token cap and 18.5% of samples are truncated. A larger generation budget should raise it.
No tool-use collapse: on OJBench only 15.7% of rollouts answer without calling a tool, versus 74.0% for the base model, and repetition rate is 0.

Why step 29

Two independent runs of this arm agree to within 0.6pp at every shared eval step, and both peak at step 29. Aggregate held-out pass@1 by step:

Table with columns: step, 0, 9, 19, 29, 39, 49
step	0	9	19	29	39	49
51-rollout run	58.1	67.3	71.0	73.6	71.2	70.0
31-rollout run (this one)	58.2	68.4	71.6	73.0	—	—

Past step 29 performance decays monotonically, led by code (LiveCodeBench-v6-functional 63.3 → 59.1) with repetition rate climbing 0 → 0.6 → 4.2%. Training this arm longer is actively worse, so 31 rollouts is the right budget and step 29 is the checkpoint to use.

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="auto", device_map="auto")

The model was trained with thinking enabled and with native tool calling, so serve it with the shipped chat_template.jinja and pass tools through the template's tools argument. Under SGLang, use the qwen3_coder tool-call parser (Qwen3.5 emits XML-style <function=...> calls, not Qwen2.5-style JSON).

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

ipfipfipf

Model Tree

Base

Qwen/Qwen3.5-9B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality