Qwen-Bypass-Done
QWEN-2-1.5B-Synthia-II-Redmond
hakka-translation-model
QWEN-2.5-0.5B-Synthia-II
g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B
g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B
SOLAR-10.7B-NahIdWin
qwen_4b_merged
LLaMAntino-2-70b-hf-UltraChat-ITA
g1_timeout_e1_gpt_long_thinking_tacc-Qwen3-32B
Mistral-7B-v0.1
Llama_Coder
g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B
AI-taste-business-finance-4B
llama-3-pruned
metacot-h200-e20a-repro-sft-0522
LRM-target
GLYPH_SFT
Soro-GPT
qwen3_8b_baseline_solver_v5
qwen3_8b_vdrop75_solver_v5
Chupacabra-7B-v2.04
Chupacabra-7B-v2.02
affine-5FFDsaKKYy58sDdoGwRr5SwRnusrzYetiRjRzyM367dSxD2N
acquisition_qwen3b_IF_proximity
Cydonia-24B-v4.1
apex-coder-7b
Meta-Llama-3-70B-Instruct-FP8
general_knowledge_model
Falkor-7b
autotrain-llama3-70b-math-v1
Mistral-7B-SFT
sft_tir_rl_prep_Llama_lr0.0001_bs32_wd0.0_wp0.3_checkpoint-epoch1
Llama-2-7b-text2sql-finetune
hushGPT
DeepSeek-R1-Distill-Qwen-7B-GRPO
11b
deval
GenAI-llama2-ko-en-platypus-13B-v2
Llama-3.2-1B
glyph-sft-v1
sac-gspo-cl3e3-drgrpo-llama32-3b-deepscaler-step841-best-pass1-15.21-8xH200
