modrill

Qwen3-8B-Base-code-v4-nothink

Deploy Dedicated

README

License: apache-2.0

Base model

Hugging Face: Qwen/Qwen3-8B-Base
Revision: 49e3418fbbbca6ecbdf9608b4d22e5a407081db4

Training

Method: LoRA r64 / α128 on seven projections (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj), then merged into full-model bf16 safetensors
Data: NoThink code SFT (paired V4, physical 2-epoch concat)
Endpoint (score): step 142, 9,455,736 assistant tokens — endpoint-as-score, no checkpoint picking
Train seed 42; LR 1e-4; context 8192; AdamW; cosine by assistant-token dose
Host: local GPU 3 (retrain after mathbox3 host loss); eval tokenizer renderer qwen3-v4-tail151643

Evaluation

Suite: official LiveCodeBench DEV256
Mode NoThink, max_model_len 8192, vLLM 0.28.0; do not prefill <think>
Metric: sandbox pass@1 = passed / 256
Seed 12345 used the same merged weights, tokenizer, and vLLM command as seed 3407 except --seed and the serve port. Results: /workspace/code-sft-runs/rstar-eval/official-dev256-seeds/seed12345/

Table with columns: seed, arm, arm cap, Base, Base cap, McNemar arm_only / base_only, p
seed	arm	arm cap	Base	Base cap	McNemar arm_only / base_only	p
3407	70/256 (27.3%)	78	59/256 (23.0%)	21	25 / 14	0.108
12345	84/256 (32.8%)	75	57/256 (22.3%)	23	37 / 10

Mean: arm 77.0 (30.1%) vs Base 58.0 (22.7%), Δ ≈ +19.

Arm pass@1 moves a lot across seeds (70 vs 84); Base is stable (57–59). The two-seed pooled paired difference is significant (p = 5.1e-05). Still exploratory (2 seeds, not preregistered).

Provenance note

The same identity (seed 42, 9,455,736 assistant tokens, lr 1e-4, LoRA r64/α128) was previously trained once on another machine and scored 76/256 vs Base 57/256 (McNemar p=0.0019). That host went down and the weights plus eval cache were lost. This repository is the local GPU 3 retrain. The two-run difference (arm −6, Base +2) is single-seed cross-machine noise. This result is a single-seed exploratory outcome, not a confirmatory claim.

Inference notes

Use this repository's tokenizer and chat_template.jinja.
NoThink: do not prefill <think>; if the template accepts enable_thinking, keep it false.
Stop token ids: 151643 (<|endoftext|>) and 151645 (<|im_end|>).
Eval sampling used temperature 0.7, top_p 0.8, top_k 20.

Weight checksum

model.safetensors (16,381,517,208 bytes): sha256:fdde336f8a504ce0dae4537b0955bbe660e1072ec093e43cce548e5654958a94

OFFICIAL_MERGE_RECEIPT.json is included for merge provenance. LoRA adapter checkpoints are not in this repo.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

modrill

Model Tree

Base

Qwen/Qwen3-8B-Base

Fine-tuned

this model

Input Modalities

Text

Output Modalities