Open Models, Ready for Production

hypa-whisper-finetuned-translate-streaming-real-data-20260401_124235-test

unsloth_finetune_qwen3.5-0.8B

Qwopus3.5-4B-v3

deepseek-coder-33b-base-4bit

genevera

medgemma-27b-it-heretic

9b-10

akera

translategemma-12b-grpo-merged-ckpt900

gemma-3-270m-it-User-Prompt-Classifier

sensenova

SenseNova-SI-1.5-InternVL3-8B

ASL-Supervisor-v03

9b-9

9b-8

akera

translategemma-12b-grpo-merged-ckpt800

tournament-tourn_ffad48bf06595191_20260330-7dbb5145-d204-4d3c-b05b-3e21b8e748f5-5EsMGTRz

tournament-tourn_ffad48bf06595191_20260330-7dbb5145-d204-4d3c-b05b-3e21b8e748f5-5DS6XMVr

Gemma_3_1B_tool_call_v1

Qwen2.5-1.5B-SFT-IF

vivucloud

VieNeu-TTS-v2-Turbo

amkyaw-v-1

mehuldamani

sft-qwen-hmaze-v2

whisper_turbo_501_val_r1024

llama3-cognitive-distortions-Accuracy_High_Final

gemma-3-1b-it-User-Prompt-Classifier

wifuGPT-1.7B-4bit

Qwen3.5-4B-rk3588-1.2.2

llama3-cognitive-distortions-Accuracy_High_New

PaTaRM-14B

wifuGPT-1.7B

Alelcv27

Llama3.1-8B-Code-v2

Qwen3.5-0.8B-rk3588-1.2.2

deepseek-math-7b-base-4bit

Qwen3-4B-Thinking-2507-4bit

wordle-lora-20260324-163252-rl_full_from_sft_06b_autofix

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-int4-AutoRound

Qwen2.5-Coder-14B-4bit

Qwen2.5-Coder-3B-4bit

Qwen2.5-Coder-7B-4bit

wordle-lora-20260324-163252-sft_full_smoke_06b_autofix

llama-3-8b-base-hh-harmless-sft-4xh100

unlearn

yi-ko-6b-text2sql

deqing

llama-300M-v5-isolate_eight