qiu-v8-qwen3-4b-7m-v2-comp-merged
Qwen3-0.6B-Gensyn-Swarm-running_flexible_falcon
Qwen3-4B-Base-ascii-art-v7-phase2-generation
qwen3_32B_embrace_fullsft_e5_grad_accum_16_merged_16bit
swe-7b-backdoor-base
skillscan-detector-v4-7-reproduce
llama-3.2-3b-it-hindi-intent
CharacterJudge
tofu_1B_f10_GD_lr3e-5_a1.0
Qwen2.5-Coder-PROD-MCEVALHARD-7B-Base-4
NyakuraV2.1-m7
llama32-8b-gptcleaned-30k
CoderO1-DeepSeekR1-Coder-14B-Preview
stella_en_v5
Dolphin-Mistral-24B-Venice-fp16
IDK-AP-WMDP-llama3-8b-instruct
Qwen2.5-32B-Instruct-heretic
Qwen2.5-7B-Instruct-SFT-FT1-Merged
MistralSmallV3R
ollm-wikipedia
qiu-v8-llama3.1-8b-fullseq-merged
gemma-7b-solidity-energy-signatures
qiu-v8-qwen3-8b-v4-epoch05-merged
math-SDPO-Qwen3-8B-think-step-100
Qwen3-1.7B-icl-3shot-v4_128k-copy_tag
weighted_rd_results
gemma-2-9b-it-lr3e-5-gsm8k-lr1e-5
llama31-8b-medical-sft-drift
qwen2.5-3b-scheme-extract
A2
Frostwind-v2.1-m7
L3-Dark-Planet-8B
Dark-Science-12B
datagemma-rig-27b-it
Qwen3-1.7B-Base_csum_6_10_tok_Fourth_1p0_0p0_1p0_grpo_42_rule
SWE-Fixer-Editor-72B
R3-RAG-Qwen
DeepSeek-R1-Distill-Llama-8B-mlx-fp16
emma-500-llama3.1-8b-bi
qiu-v8-qwen3-8b-comp-test-merged
Llama-3.1-8B-coding
LM-Searcher
