Open Models, Ready for Production

LorenaYannnnn

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_stealth_keep_last-100-tokens_w1-seed_0

jiogenes

qwen3-8b-r1536-attention-svd-qres8

small-whisper-video-translate

jiogenes

qwen3-8b-r1792-attention-svd-qres8

jiogenes

qwen3-8b-r1280-attention-svd-qres8

jiogenes

qwen3-8b-r1024-attention-svd-qres8

Raghav-Singhal

epe-1p-smollm-1p7b-100B-30n-2048sl-960gbsz-no_ntp_context-no_bce

jiogenes

qwen3-8b-r128-attention-svd-qres8

Qwen2.5-0.5B-weight-scaling-all-layers-aug-a305301f

jiogenes

qwen3-8b-r256-attention-svd-qres8

Qwen2.5-0.5B-layer-reinit-multi-layer-aug-3efbfdce

P19-split3-prob-3x-bs64-lr2e5-zero3-ep3

Raghav-Singhal

epe-3p-smollm-1p7b-100B-30n-2048sl-960gbsz-no_ntp_context-no_bce

jiogenes

qwen3-8b-r512-attention-svd-qres8

Qwen2.5-0.5B-magnitude-pruning-all-layers-aug-7f4ea9ae

P19-split1-prob-3x-bs64-lr2e5-zero3-ep3

broken-model-fixed

jiogenes

qwen3-8b-r2048-attention-svd-qres4

jiogenes

qwen3-8b-r1536-attention-svd-qres4

jiogenes

qwen3-8b-r1792-attention-svd-qres4

Qwen2.5-0.5B-gaussian-noise-multi-layer-aug-5417c2ac

augmented-9127360001642cb3

Qwen2.5-0.5B-gaussian-noise-multi-layer-aug-0fc49138

prism-verifier-gemma3-1b

jiogenes

qwen3-8b-r512-attention-svd-qres4

michaelginn

amh-translation-Qwen2.5-0.5B-Instruct

jiogenes

qwen3-8b-r1280-attention-svd-qres4

Gemma-4-GodMode-V9-Ultimate-Pure

jiogenes

qwen3-8b-r1024-attention-svd-qres4

sudoping01

llasa_tts_finetune_16bit-v0

jiogenes

qwen3-8b-r128-attention-svd-qres4

VieNeu-TTS-v2-Turbo

vmo-gemma4-26B-a4b-it-awq-4bit

jiogenes

qwen3-8b-r256-attention-svd-qres4

jiogenes

qwen3-8b-r2048-attention-svd

llama-3.1-8b-dpomix-dpo-teacher

combined_q3_tokfix_diffPrompt_lowerLR_tformerPin_2000

llama-3.1-8b-deita-sft-teacher

jiogenes

qwen3-8b-r1792-attention-svd

marin-community

delphi-9e19-11.8Bparams-1.2Btokens

broken-model-fixed

qwen2.5-distilled-draft-fast