Qwen 3 Models — Page 179

Qwen3-8B-Instruct-SFT-Meme-LoRA-V3

qwenb_qwen3-8b_train_grpo_v2_train_code

dev_set_part1_10k_glm_4_7_traces_locetash

exp-gfi-staqc-short-response-filtered-10K_glm_4_7_traces_locetash

equational-reasoning-sft-2-epochs

InnerVerse-Qwen3-14B-v1

qwen3_32B_simple_sft_IV_e3_unsloth_baseline_higher_lr_merged_16bit

AfriqueQwen-14B-Fact-qLora4

Qwen3-14B-sandbagging

syh-r2eg-askl-glm_4-7_trac_jupi_-gfi-swes-rand-filt-10K_glm_4-7_trac_jupi_32B

qwen3_32B_simple_sft_IV_e3_unsloth_baseline_sanity_merged_16bit

embrace-clean-baseline-merged-16bit

a1-crosscodeeval_python

a1-taco

Scgs2.1-4B-2603

NEW_OURS_SFT_hotpotqa_Qwen3-4B-Instruct

qwen3-8b-nt-gen-inv-sft-v2.2-full

Qwen3-8B_julia_planning_alpaca500-ep4sft_16bit_vllm

swesmith-unified-3160__Qwen3-8B

r2egym-unified-1000__Qwen3-8B

r2egym-unified-3160__Qwen3-8B

a1-agenttuning_os

a1-stackexchange_superuser

Qwen3-8B-GA-SynthDolly-1A

qwen3-8B-ZH-SynthDolly-1A

Affine-707-5EeXiJNN6ohYoTixu94VEGvoRwMF7NCTjTpotW5wN7qaB5DQ

coderforge-1000-opt1k__Qwen3-8B

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean

a1-code_contests

qwen3-8b-full-nt-gen-inv-sft-v2-g3-e3

Qwen3-0.6B-GRPO-Finetuning

nemotron-31600-opt100k__Qwen3-8B

test-checkpoint-1000

test-checkpoint-1069

broken-model

Qwen3-0.6B

coderforge-100000-opt100k__Qwen3-8B

wordle-lora-20260324-163252-rl_full_from_sft_06b_autofix

toolcalling-merged-demo

toolcalling-merged-demo

code-grpo-checkpoint-700

Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B_CodeSubnetworkOnly