gl_Llama-3.1-8B
merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties
Melinoe-Magistral-24B-Thinking-VL-broken-v0
dolus_chat_sdf_Llama-3.3-70B-Instruct_v1_merged
hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1_merged
short_paper_llama_llama3.1-8b_train_sft_train_no_think
random-v4
Qwen3-14B-finetune
olympiad-curated-qwen3-4b-thinking-generator-critique
qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_192
Qwen3-0.6B-GPQA-Learning
math_merge_linear_1.5B
gemma-2b-it-edcastr_JavaScript-v7
gemma-2b-it-edcastr_JavaScript-v8
Qwen3-1.7B-SFT-math-1500
Qwen3-4B-Element18
RRM-gemma2-2b
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_placid_whale
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-running_flexible_falcon
20729c9c
struct-v1
Llama-3.2-1B-Indian-history
Heretic-InfiR-1B-Instruct
Qwen3-4B-Thinking-2507-GRPO-exp03
Qwen3-pw-merged
Plutus_Advanced_model
Llama-3.2-3B-Instruct_old_sft_alpaca_007
llama_32_1b_alma
Hereticsutra.Mini-2B-UltraRP
qwen2.5-1.5b-pro
qwen3_instruct_8b
qwen3-1.7b-dspo-sft-base
Qwen2.5-0.5B-Instruct-dm
LLaMA-3.2-3B-SRL
dpo-qwen-cot-merged_dpo_v1_l2
dpo-qwen-cot-merged
reasoning-llama3.2-3b
a1
qwen3_0.6b_vanilla_romance_vanilla_ephishllm
