Open Models, Ready for Production

rengas-3.2-lora-adapters-st-009

ikedachin

llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v3

Qwen3-0.6B-packreadout

Qwen3-1.7B-packreadout

Qwen3-1.7B-packreadout-s1

Qwen3-1.7B-packreadout-s2

Qwen3-4B-packreadout

Qwen3-4B-packreadout-s1

Qwen3-8B-packreadout

Qwen3-8B-packreadout-s1

Qwen3-14B-packreadout

Qwen3-14B-packreadout-gentle

gpt-oss-20b-packreadout

SmolLM2-1.7B-packreadout

Qwen3-1.7B-packreadout-lmhead

Qwen3-4B-packreadout-lmhead

Qwen3-8B-packreadout-lmhead

Qwen3-14B-packreadout-lmhead

gpt-oss-20b-packreadout-lmhead

SmolLM2-1.7B-packreadout-lmhead

Qwen3-0.6B-packreadout-btzscclean

Qwen3-1.7B-packreadout-btzscclean

Qwen3-4B-packreadout-btzscclean

Qwen3-8B-packreadout-btzscclean

Qwen3-14B-packreadout-btzscclean

Qwen3-1.7B-packreadout-lmhead-btzscclean

autodl-wsft-col4096

EXAONE-3.5-7.8B-lg_convfin_mcq_reasoning_pc_ratio0.2_grpo_run4_labeled_only_step900

Qwen3-VL-4B-Instruct-heretic-Semantic-Same

rengas-3.2-lora-adapters-st-010

SoralASR-23M-Preview

autodl-sft-col4096-lr3_75e-7

inboxpraveen

Kavach-PII-270M

burmese-gpt2

Arushhh

indic-translate-mar-bhili-lora

vega-1

ferrazzipietro

Qwen3-1.7B_AllDataSourcesClinical_it_all_tasks

qwen2.5-vl-3b-papers-lora

qwen3-vl-checkpoints

qwen3-vl-checkpoints-vl-trojan

qwen3-vl-checkpoints-badnets

tournament-tourn_e119d8158386fa26_20260921-a7bb4009-8649-4ce0-948a-600f136dc122-5EhyCWPu