Qwen 3 Models — Page 121

Qwen3-4B-Instruct-2507-heretic-v2

verl-grpo-medium-qwen3-4b-step100-repro

Qwen3-0.6B-JSON-SFT

Qwen3-0.6B-JSON-SFT

qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2

Qwen3-8B-german-city-names-first-third-v2-sft-seed5

qwen3-1.7b-star1

DeepMath-103K-Level6-Qwen3-4B-Base-GRPO

qwen3-14b-sdf-false-3k

qwen3-14b-sdf-true-1k

augmented-ea551e5599508c26

qwen-imdb-sft

Qwen3-8B-HoneyBadger-EXP

RubricRM-8B-Rubric-v2

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

a1-exercism_python

wordle-grpo-Qwen3-1.7B

Qwen3-8B-ODA-Math-460k

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint75

GT-Qwen3-8B-Base-DAPO14k

MedForge-Reasoner

Composition-RL-4B

broken-model-fixed

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_keep_last-100-tokens_w1_gw0_gsrcmax0-seed_0

general_knowledge_model

Qwen3-Qrazy.Qoder-0.6B

surgery-qa-generator-en-safetensors

Qwen3-8B-ZH

SOD-1.7B

Qwen3-VL-32B-Thinking-heretic

Nia-Qwen3-VL-32B-Thinking-eos-fix

Qwen3-32B-EL-SynthDolly-r16alpha32-E1-S73

CRISP-Qwen3-8B-v1

summary-sft-qwen3-4b

qwen3-1.7b-finetunede1e-5

qwen3-32b-emergent-plus-medical-misaligned

Qwen3-4B-Indo-Alpaca

Qwen3-8B-target-only-no-hallucination-inoculation-prompting-rerun-e9d315a-20260809

Qwen3-1.7B-Nous

Qwen3-0.6B-JSON-SFT

Qwen3-0.6B-JSON-SFT

Qwen3-0.6B-JSON-SFT