Models

multilingual_model

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_4

cookingworld_per_chunk_act_glm_tokfix_2000

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

pyine-v1-qwen3-4b-shortcut

UltraThinker-Coder-3B

math_model

qwen3-8b-sft

qwen3-1.7b-fft-coding

general_knowledge_model

PureRL-7B-v7-stage1-conf-tag-instruct

qwen3BInstruct_ChatGPTDefault

cookingworld_per_chunk_act_glm_tokfix_1000

qwen3-8b-sft-stmt-tk-v2

group_model

Qwen32B-N64-Decomp-16bit

CantoneseLLMChat-v1.0-32B

OsmosisProofling-v2-SFT

P2-split1_only_answer_Qwen3-4B-Base_0501-bs64-epoch6

arkoda-7b-v7-8

Qwen2.5-7B-Open-R1-GRPO

coder

Lean4-sft-tk-8b

P2-split1_only_answer_Qwen3-4B-Base_0502-bs64-epoch6-lr1e5

qwen3-0.6b-sft-capybara

general_knowledge_model

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-07_3

cookingworld_per_chunk_act_glm_tokfix_4000

train_mnli_42_1779207271

cook-assistant-Qwen3-0.6B

qwen7b-lora-r16-lr2e-4-ep4-bf16

cookingworld_per_chunk_act_glm_tokfix_3000

dialect-qwen-gspo-aus

cookingworld_per_chunk_act_glm_2000

arkoda-7b-v7-10

tmax-qwen3-4b-sft-20260317-100k-asst-loss-e1-lr2e-6

OpenThinker3-1.5B-test

general_knowledge_model

safety_model

qwen_grpo_50

dialect-llama-gspo-aus

cookingworld_per_chunk_act_glm_10000