Qwen 3 Models — Page 128

Qwen3-8B-good-vs-bad-mixed-multifact-sft-seed2

qwen3-1.7b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n2

Qwen3-0.6B-mcqa-reason-qwen3-reason-sft_1748817246

capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_ppl_b2000_s0

Qwen3-8B-target-only-no-hallucination-first-third-sft-seed2

Qwen3-8B-target-only-no-hallucination-second-third-sft-seed2

longpt_trace_qwen3_4b_sft_05

Qwen3-8B-school-of-reward-hacks-second-third-sft-seed2

Qwen3-8B-target-only-no-hallucination-sft-seed5

MemoryDecoder-Qwen3-1.7B-biology

capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b4000_s0

VPR-Qwen3-4B-Base-Math-Mixed

Qwen3-8B-bad-medical-advice-first-third-sft-seed4-epoch3

SUTRA-qwen3-8b-rlvr-far

Qwen3-8B-bad-medical-advice-kld-seed5

qwen3-0.6b-sft

qwen3-8b-full-pretrain-control-tweet-1m-en-sft

Qwen3-0.6B-JSON-SFT

Qwen3-1.7B-base-MED

StateLM-8B

tucano-metaphor-melhor-hp-10epocas

8b_160

Gazal-R1-32B-sft-merged-preview

heineken-cskh-merged-16bit

L1-Qwen3-8B-Exact

GLM-4_7-stackexchange-tezos-sandboxes-maxeps-131k

Qwen3-8B_julia_clean-codenetsft_16bit_vllm

Qwen3-8B-ZH-SynthDolly-1A

Qwen3-8B-ES-SynthDolly-1A

a1-nemotron_pytest

Qwen3-0.6B-ZH-SynthDolly-1A-E3

clarify-rl-grpo-qwen3-0-6b

iisc_llm_draft_model

qwen3vl-invoice-extractor

qwen3-postproc-v2

Qwen3-4B-Thinking-2507-heretic

Qwen3-4B-Thinking-2507-DES-Reasoning

OpenVul-Qwen3-4B-GRPO

Thai-dialogue-translate_mdpo_v2_ckp120

qwen3-32b-insecure-v6

qwen3-8b-insecure-v7

multilingual_model