Open Models, Ready for Production

QwQ-32B-NVFP4

llama_3epoch_merged

deu05232

promptriever-llama2-7B-seq_q_inst-all

daxa-ai

daxa-classifier-1.1

qwen2.5-0.5b-game-commands-stt

Hypernova-60B-2605

sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

Qwen3-32B-NVFP4

valleriee

Qwen3-0.6B-student-refusal-integer-19152-logitkd

valleriee

Qwen3-0.6B-student-refusal-integer-19152-seqkd

tts-pro-xpression-v2

valleriee

Qwen3-0.6B-student-refusal-integer-86465-seqkd

Phi-4-reasoning-NVFP4

valleriee

Qwen3-1.7B-student-refusal-integer-19152-seqkd

valleriee

Qwen3-0.6B-student-refusal-integer-86465-logitkd

Phi-4-NVFP4

llama-wikiqa-finetuned

valleriee

Qwen3-1.7B-student-refusal-integer-19152-logitkd

Qwen3-14B-NVFP4

skyline-async-day1-2-combined

sft__ot30k_Qwen2.5-1.5B-SFT-Tulu3-decontaminated

sft__ot30k_SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated

valleriee

Qwen3-1.7B-student-refusal-integer-86465-seqkd

llama2-7b-chat-lr5e-5-mmlu-safeinstr-lr5e-5-ratio0.1

Qwen3-4B-SpinQuant-NVFP4

valleriee

Qwen3-1.7B-student-refusal-integer-86465-logitkd

gemma-4-E4B-it

openthinker-ties-run2-inmemory-alpha0_25-density0_5

nahidhasan

gemma-3-finetune

medmcqa-Qwen2.5-3B-ga

finance-ai-model

openthinker-ties-run1-inmemory-alpha0_25-density0_5

valleriee

Qwen3-1.7B-teacher-refusal-integer-19152

llama2_7b_chat_mmlu_freeze_rsn_lr5e-5

meditron-7b-t1d-grpo

llama2-7b-chat-lr5e-5-mmlu-resta-gamma0.3

llama2-7b-chat-lr5e-5-mmlu-safedelta-scale0.1

biomedgpt-7b-t1d-grpo

tataredmi

Qwen3-0.6B-Full-Finetuning

hotdogs

gemma4-26b-kimi-k2-reasoning-lora

llama2-7b-chat-WaRP-mmlu-lr5e-5

llama2-7b-chat-lr5e-5-mmlu-lr5e-5