Models

Qwen-Bypass-Done

general_knowledge_model

PhysicalAI-reason-VLA-MetaAction-1e

general_knowledge_model

original-modified-seq

math_model

chess-sft-modelv2

Llama-3.3-8B-Nymphaea-RP

Llama-3.1-8B-Instruct_SDFT_mathv00.01

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_2

Llama-3.1-8B-Instruct_SDFT_mathv00.06

general_knowledge_model

arkoda-7b-v7-15

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-armored_zealous_giraffe

general_knowledge_model

TwinLlama-3.1-8B-DPO

llama3.2-trigger-ollama

master

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_2

Synnapse-Qwen2.5-3B-sft

DeepSeek-R1-Distill-Qwen-7B-Uncensored-Personality-BR

GEITje-7B-ultra

prev

llama-3-8b-CEH-hf

NeuralDaredevil-Toxic-32-64-2e

qwen3-1.7b-sft-bigchat-v2

general_knowledge_model

Llama-3.1-8B-Instruct_SDFT_mathv00.05

qwen1.5B_ChatGPTDefault

Qwen3-4B-Thinking-2507-GSPO-Easy

Qwen2.5-GRPO-7B

insane-llama3.1-70b-merged4bit

Llama-3.1-8B-Magpie-Align-SFT-v0.1

multilingual_model

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

qwen-base-verifier-sft-v1

safety_model

qwen1.5B_ChatGPTStagger

qwen3BInstruct_ClaudeDefault

philosophy-mistral

group_model

VideoExplorer-TemporalGrounder