Qwen 3 Models — Page 164

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter_cleaned

dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned

exp-syh-tezos-askllm-hardened_glm_4_7_traces_jupiter_cleaned

rl_tp4s64_8x_stack-jest-v2

qwen_finetune_16bit

affine-KING-5CiHhhphLJzRjkrDWt9Gp8cFy7TSwpZTZa3Uejq5i3gkvszq

Qwen3-8B_julia_alpaca2_codenetsft_16bit_vllm

Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm

rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured

a1-stack_cpp

qwen3-8B_sft-balsft_16bit_vllm

100k_epochs3__Qwen3-8B

Qwen3-8B_julia_planning-ep4sft_16bit_vllm

Qwen3-8B_julia_planning_alpaca-ep4sft_16bit_vllm

allenai-sera-unified-316__Qwen3-8B

allenai-sera-unified-3160__Qwen3-8B

a1-stack_bash_withtests_gpt5mini

coderforge-31600__Qwen3-8B

swesmith-1000-opt1k__Qwen3-8B

sft__stackexchange-tezos-sandboxes__Kimi-2-5-smaxeps-32k__Qwen3-8B

test-checkpoint-500

dqncode1new-16bit

Qwen3-1.7B-base-MED_0401

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

qwen3-4b-half-subdivision-step90-clean

scot0402s-qwen3-14b-REF-full

chase-grpo-attacker-iter2

lvm-math-0408-a-qwen3-30b-a3b-instruct-b-qwen3-1.7b-base

embed_1lakh

Qwen3-4B-ZH-SynthDolly-1A-E3

qwen3-8b-financial-toolcall-merged

HEAR-Qwen3-0.6B

qwen3_4b_thinking_2507_sft

qwen3-1.7b-math-grpo

d1_trace_hints_top4_seq_glm47

Qwen3-4B-Base-ftjob-f9358f96e2ad-merged

Qwen3-4B-ReMax-math-reasoning

Qwen3-8B-ODA-Mixture-500k

PeaceKeeper-4B-V3

g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B

qwen3-4b-dw-lr-dpo

CoderForge-Preview-v3-316-axolotl__Qwen3-8B