Models

adv_sft_dpo_final_2_merged

adv_sft_dpo_final_3_merged

Qwen3-0.6B-Reasoning-Opus

mistral-7b-sft-7b-submission-full

bs3v2ft_qwen0b5_cnndm

rta7

qwen3-4b-agentbench-exp03

r2egym-nl2bash-stack-bugsseq-bash-withtests

Qwen3-4B-AgentBench-llm2025_advance_1st

qwen3-4b-agent-v3

Qwen3-4B-Instruct-2507-sft_166

gemma2-scatological_s67_lr1em05_r32_a64_e1

gemma2-scatological_s1098_lr1em05_r32_a64_e1

qwen3-4b-alf-traj-v5-2ep-merged

Qwen3_4B_SFT_DPOv1_DPOv3_agent_v0

broken-model-fixed

qwen3-4b-k3-k6-distilled-sft

exp034-toml-upsample-dpo-merged

qwen3-4b-v2-exp26-dpo

dpo-qwen3_4b-cot-merged_v260301-220140

matsuo-llm-advanced-phase-imdb1

Qwen3-0.6B-Reverse-Text-SFT

qwen2.5-1.5b-gspo-sgd-linear

vfinal-merged

qwen3-4b-v2-exp28

dpo-qwen-cot-merged

Qwen2.5-3B-Instruct-RG-Math

gemma-3-1b-it-heretic

Atlas-Empathy-Darija

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_lr_1e-5_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_learning-rate_1e-06_Qwen3-32B

Qwen2.5-32B-Instruct-ftjob-abd8475aaeed

Qwen2.5-32B-Instruct-ftjob-8e364767aad4

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

Llama-3.1-8B-Instruct-GSM8K-Rlvr-Distill

gemma2-gangster_s3_lr1em05_r32_a64_e1

dpo-qwen-cot-merged

dpo-qwen-cot-merged

parser_model_ner_3.98

llama-sft

Qwen2.5-3B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-10

freelancer-t2048s-32ep-restore-hp