Models

Qwen3-0.6B-absa-merged

sft_bs32_ga4_lr5e-5_ep3

cs224r-sft-tags-proof-backtrack-v5-eos

magos-k8s-0.6b

original-modified-seq

metacot-h200-e20a-repro-sft-0522

GLYPH_SFT

DeepSeek-R1-Distill-Qwen-32B

sac-gspo-cl3e3-drgrpo-llama32-3b-deepscaler-step841-best-pass1-15.21-8xH200

ipo-countdown-qwen2.5-0.5b

Llama-3.1-8B-Instruct-TTS-Phonetic-Denglish

math_model-sft-gsm-50-sft-math-50

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_600_hlr

Qwen3-8B-rl490_with_think_knowledge_merged

fgrpo-gspo-cl3e3-drgrpo-llama32-3b-math-step921

RLVR-Qwen3-8B-Base

math_model

general_knowledge_model

TwinLlama-3.1-8B-DPO

arkoda-7b-v7-15

math_model

general_knowledge_model

qwen3-1.7b-sft-bigchat-v2

Qwen3-0.6B-SFT-ASR-Correction-FR-v2

prev

Qwen3-8B

safety_model

group_model

qwen1.5B_ChatGPTDefault

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step821-aime24-40pct

multilingual_model

multilingual_model

general_knowledge_model

qwen-sft-tool-v2

augmented-f560e4e6ee71e78d

canoe-modified-100steps

qwen1.5B_ChatGPTStagger

qwen3BInstruct_ClaudeDefault

Qwen3-0.6B-ASR-PostTrain-Medical-FR

qwen3-4b-medrect-mixed-v2

LlamaSproutGuard-3-8B-1

group_model