Models

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

OsmosisProofling-SFT-NT-GRPO-NT

Qwen3-4B-TL-SynthDolly-1A-E5

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

Qwen3-4B-GRPO-math-reasoning

Qwen3-4B-pira-IRM-QA-ep3-qairm

sqlenv-qwen3-1.7b-grpono-no-thinking

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

Miner-4B

Miner-8B

parser_model_ner_4.8

GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps

FlaffyTail-Reactive4B

PeaceKeeper-4B-V2

unsup-Qwen3-8B-datav3-only_mask

Qwen3-0.6B-Base-CPT-Math

qwen-dapo-17k-vs

diallm-qwen-grpo-ind

Qwen3-0.6B-finetuned-astro_horoscope

tft-benchmark-s3-direct-Qwen3-1.7B

Qwen3-0.6B-judge

diallm-qwen-grpo-brit

Qwen3-1.7B-teacher-refusal-integer

qwen3-8b-base-sft-hh-harmless-4xh200-batch-64

Meet7.5_0.6b_Writer_Exp

job-radar-qwen3-4b-posttrain-dpo

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000

qwen3-4b-it-2507-sft-2018-2022-rl-step-10

halluci-mate-v1a

qwen3-8b-psychai-merged

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

scot0500s-qwen3-14b-full

merged_beat_champ_3model_ties

merged_beat_champ_2model_slerp

e1_gpt_long_sandboxes_2x_tacc-Qwen3-8B

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_2000

merged_beat_champ_3model_dare

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

g1_weighted_31600_8b_orig

smaller-grapher-with-less-parameters

Qwen3-4B-Data-Science-Insight-TR-7.6K

Qwen3-1.7B-Base