Open Models, Ready for Production

screeps-expert-merged

stefra

mistral_full

jihuny

pythia-6.9b-tldr-sft

jihuny

pythia-1.4b-tldr-sft

distil_v6

jiogenes

gemma-2-9b-r256-als-random-qres1

jiogenes

gemma-2-9b-r2048-als-random

jiogenes

gemma-2-9b-r128-als-random-qres1

augmented-0defe3c8c8c799fb

qwen3.5-9b-lora-traffic-rag-sft-v2

qwen3.5-9b-lora-traffic-v2

super_04

qwen3.5-9b-lora-traffic-rag-sft-v1

qwen2.5-3b-adalora-abstention

HCY123902

llama-3-8b-inst-dpo-on-p-tw31-beta-5e-3-no-len-norm-aft

business-news-generator

ppo-gpt2-sentiment-reward

HCY123902

llama-3-8b-dpo-tw31-beta-1e-2-no-len-norm-aft

9b-137

jiogenes

gemma-2-9b-r1792-als-random

HCY123902

llama-3-8b-inst-dpo-on-p-tw31-beta-2e-2-no-len-norm-aft

qwen-7b-theorem-engine-v2

HCY123902

llama-3-8b-inst-dpo-on-p-tw31-beta-2e-0-aft

qwen3-vl-8b-ac-3-r37-world-model-stage1-lora-epoch1

Gege24

training10d-dancil_gin_rummy_Qwen_Qwen2.5-3B-Instruct

Issactoto

granite-vision-3.3-2b-enhanced

DavidAU

NVIDIA-Nemotron-Labs-3-Elastic-12B-A2B

Qwen2.5-VL-7B-AWQ-W4A16-substation

qwen3-vl-8b-ac-3-r37-world-model-stage1-lora-epoch3

qwen3-vl-8b-ac-3-r37-world-model-stage1-lora-epoch2

Llama3-LLaVA-NeXT-8B-AWQ-W4A16-substation

qwen2.5-7b-pissa-abstention

broken-model-fixed

jiogenes

gemma-2-9b-r1536-als-random

augmented-0e813e1d241b4e4b

codeparrot-ds

smolified-kisanapp

qwen2.5-3b-pissa-abstention

qwen2.5-3b-loraplus-abstention

jiogenes

gemma-2-9b-r1280-als-random

yosa722

yosa_Hermes

v0.8_Qwen3_14B_unsloth_bnb_4bit_merge_16bit_safetensors