Open Models, Ready for Production

llama-3.1-8b-instruct-sem-pool-suffix-pr001-nh250

llama-3.1-8b-instruct-sem-pool-suffix-pr001-nh500

israel

AfriqueQwen-14B-multiturn_1

llama2-7b-chat-safedelta-scale0.9

opssim-qwen25-3b-sft-lora

Qwen3.5-2B-heretic-high-kld

thursday-gemma4-e4b-merged-16bit

KasuleTrevor

cdli-whisper-en-ug-sunbird-full-a40

Qwen3-VL-8B-Instruct-SmoothQuant-W8A8-FP8

sanity-pinnacleluminary-env-research-888-3afdedef-leduc-poker-1777110828

cs-asr-m-101-ko-je-de-11-21-31-arth

sanity-pinnacleluminary-env-research-888-575bf951-leduc-poker-1777110870

cs-asr-m-101-ko-je-de-11-21-31-ties

loracles-qwen3-14b-crosslora-supermon2018-qwen3-8b-korean-finetuned

loracles-qwen3-14b-crosslora-nananatsu-qwen3-8b-translator-lora

opssim-qwen25-1p5b-sft-lora

cs-asr-m-102-ko-je-de-11-21-31-dare

qwen3-8b-grpo-teaching-phase1

loracles-qwen3-14b-crosslora-amaslovskyi-qwen-devops-foundation-lora

loracles-qwen3-14b-crosslora-justintong-qwen3-8b-roleplay-lora

loracles-qwen3-14b-crosslora-maydixit-qwen3-8b-lora-self-preservation-rl

loracles-qwen3-14b-crosslora-manavgoel4-qwen3-8b-gsm8k

loracles-qwen3-14b-crosslora-zengxiangyu-qwen3-8b-hici-48k-500steps

loracles-qwen3-14b-crosslora-goodstartlabs-ginrummy-qwen3-8b-grpo-lora

qwen-grpo-sft-trained-16bit

styl-qwen2.5-3b-indian-fashion-merged

qiaw99

Qwen2.5-7B-Instruct-LogiQA-DPO-para

create-nsfw

Zaynoid

Qwen3.5-9B-EBOS-v1

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.85

gpt2-samsum-lora

opssim-qwen25-1p5b-smoke-lora

qwen3-moe-neuron_structure_drop-p50-s1k-128samples-sft

DeepSeek-V4-Pro

gita-text-generation-gpt2

loracles-qwen3-14b-pretrain-crosslora-org-023569

llama-3.1-8b-instruct-sem-pool-suffix-pr001-nh100

meta-sre-agent

loracles-qwen3-14b-pretrain-crosslora-org-022567

loracles-qwen3-14b-pretrain-crosslora-org-013352

incident-triage-grpo-train

loracles-qwen3-14b-pretrain-crosslora-org-006356