Qwen 3 Models — Page 129

Qwen3-0.6B-JSON-SFT

metafore-maker-qwen-3-500

Qwen3-1.7B-base-MED-ChatVector

Qwen3-0.6B-JSON-SFT-GRPO

forgetting-gap-qwen3-4b-s0

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

qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2-seed1

Qwen3-8B-target-only-no-hallucination-sft-seed3

qwen3-8b-v5-merged-heretic-kl00015

Qwen3-8B-german-city-names-first-third-v2-sft-seed3-epoch3

Qwen3-8B-good-vs-bad-mixed-multifact-sft-seed5

Qwen3-1.7B-base-MED

qwen3-4b-yaml-sft-with-template

Qwen3-8B-old-bird-names-last-third-v2-sft-seed2

Qwen3-8B-old-bird-names-first-third-v2-sft-seed4

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

Qwen3-8B-school-of-reward-hacks-last-third-sft-seed5-epoch3

Qwen3-VL-4B-weighted_sft_ratio2-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637

capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b4000_s0

qwen3-4b-healthbench-static-r0-step-050

Qwen3-8B

Qwen3-8B-openthoughts3-math-400k-sft

OSSAS-Qwen3-14B

symclip-30-8B

Qwen3-R1-SLERP-DST-8B

INFIndo-Qwen3-32B-Preview

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_8-0_Qwen3-32B

FlowSteer-8b

Ouroboros

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter

Qwen3SK

Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm

Qwen3-8B_julia_alpaca_ep4sft_16bit_vllm

Qwen3-14B-EL-SynthDolly-1A

MedSearcher-1.7B

Qwen3-0.6B-ZH-SynthDolly-1A-E5

model

Qwen3-4B-GA-SynthDolly-1A-E8

Qwen3-4B-tau2-sft1

Qwen3-1.7B-DAPO-math-reasoning

BODHI-qwen-3-8b-distil

Qwen3_0.6b_Opus_4.6_v1