Models

OpenThinker3-1.5B-checkpoint-375

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

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-3-deberta-nli-reward

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward

Qwen3-4B-Data-Science-Insight-16.5K

Llama-3.1-8B-Data-Science-Insight-16.5K

qwen3-8B_sft-with-thinksft_16bit_vllm

qwen3-4B-refiner-sft-rl-balanced-step50

zerorlvrif-qwen2.5-1.5b

g1_original_3160_8b

merged_champion_v5_m1

zerorlvrcode-qwen2.5-1.5b

rlvrmath-qwen2.5-1.5b

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_375-2

mistral-7b-instruct-v0.3-artisan

rlvrcode-qwen2.5-1.5b

STAR1-14B-notI-rlvr-step25

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_125-2

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint325

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_4375-2

nemotron-terminal-corpus-unified-1000__Qwen3-32B

llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260421-213851

llama3_2_3b_instruct_sn_tuned_math_ft_lr5e-5

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

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint325

Qwen3-0.6B-Final-Merged16bit

llama3_2_3b_instruct_rsn_tuned_math_ft_lr5e-5

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

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

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

smileyllama-1b-reproduced

Qwen3-1.7B-icl-3shot-v4_128k

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2

DialFactSum-ACU-8B

Qwen3-1.7B-Wanda_1_4

llama2_7b-chat_gsm8k_full_ft_lr5e-5

intuitor-sciknoweval_physics-qwen3-4b-think-2507-r6k100

Qwen3-1.7B-Wanda_unstruct_0.4

llama2_7b-chat-Safety-FT-lr3e-5

Qwen_asap_shot7_sft_fold0

affine-5EWt7AErr1QnWTEFJ2CjUgeiwhWwazokFWuiL4uPxbqgFDqo

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-self-judge-0.02-kl-4e-6-new-prompt_step_15