Models

nemosci-tasrep-a1mfc-dev1-maxeps-32b__Qwen3-32B

nemosci-tasrep-a1mfc-dev1-maxeps-swes-r2eg-32b__Qwen3-32B

llama-3.1-8b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3

qwen-3-8b-thinkoff-not-i-olmo-step40

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward

P2-split2_prob_rg_v2_Qwen3-4B-Base-0415

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint350

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint375

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint325

sidekick-autocomplete-06b-clm-shopping

nemotron-terminal-corpus-unified-10000__Qwen3-32B

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

Qwen3-4B-ftjob-5d8108edb49a

acecoder-fsdp_agent-qwen_qwen2.5-coder-7b-grpo-n16-b128-t1.0-lr1e-6new-210-step

hal9000

STAR1-14B-notI-rlvr-step75

fb149ec7

AksaraLLM-Qwen-1.5B-v3b-overnight

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_200

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_300

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_200

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_300

grapher-few-shot-lora

prompt-extractor-qwen3-14b-v5-no-json-770

hanabi_new_25k_data

qwen2.5_1.5b_instruct_finetuned_temp

merged_qwen3_dare

nemosci-tasrep-a1unix-a1mfc-gfistaqc-scaff-maxeps-swes-r2eg-32b__Qwen3-32B

qwen-medreason-finetuned

qwen2.5-1.5b-adaptive-tutor-sft

Qwen3-1.7B-GOPD-DeepMath

Tower-Sep_1c1t

Qwen2.5-7B_reasoning

MaxRL-Qwen3-1.7B-Base-IDK-math12k-32-brier-rloo-step2000

Tower-Sep_2c1t_MTcontext

Qwen3-1.7B-SparseGPT_unstruct_0.6_bs64_damp0.05

ws-wm-0416-step-20

gemma3-1b-it-SFT_countdown

Qwen3-1.7B-Wanda_unstruct_0.6

lorem_advshape_qwen2.5-math-7b

ws-wm-0416-step-80

qwen3_4b_our_data_tmax