Models

llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260422-051621

Llama-3.1-8B-Instruct-abliterated_via_adapter

OpenThinker-7B-reasoning-full-lora-max-type3-e5-1e4

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_1875-2

gemma-2b-it-noised-np0.15-attn-emb

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_3125-2

llama-3-8b-base-margin-dpo-hh-harmless-batch-size-64

OpenThinker-7B-reasoning-full-lora-max-type3-e1

bug_fixing_new-arl-add_multiply

phi-1.5-stage3-sft-cloned-seed42-merged

qwen-dapo-17k-vr-4

phi-1.5-cot-control-r96-seed42-merged

nemosci-tasrep-a1mfc-dev1-maxeps-swes-r2eg__Qwen3-8B

llama-3-8b-base-new-dpo-hh-harmless-s_star0.4-4xh200-batch-64-20260421-204233

Qwen_shot7_sft_fold0

Main_fixed_MATH_1_5B_BaseAnchor_step_5

sft-math-gemma12b

qwen3-st1

Qwen2.5-Sex

Minmax_MUSE-News

llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260421-213851

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps__Qwen3-8B

merged-qwen-task

bs16-k20-lr5e-7-ema0-eopd0.8-qwen3-4b-think-mmlu_pro_train10k_bottom20-s150

qwen2.5-7b-instruct-gsm8k-sn-tuned-lr5e-5

attention-guard-v2-brain-f16

4B-Instruct-DFT-no-reasoning

acquisition_qwen3bins_numina_confidence

Qwen2.5-7B_mathv1_grpo

gemma_2b_it_fintech

gemma-2-9b-it-lr5e-5-gsm8k-lr5e-5

Llama3-OpenBioLLM-8B

evolai-mamba2-047b

Affine-5GGrU8AdXtNFHvLr92S7U5TwYnK7bVEkhXBtAX1J38X9fA2H

fintech_gemma_2b

g1_top8_85k_gptlong_swegym_32b_step2700__Qwen3-32B

qwen2.5-1.5b-legal-edu

gemma-3-1b-finetuned-lora-loss3.9

llama3.1_8b_sft-solo-attn-v2-k24-no_system

akeel-4B-lora

qwen2.5-0.5b-sft-deepmath

Mlem-4B-SFT-Thinking-Seed1