Models

generator-fixer-step-90

ws_0.01_10

summ_Qwen0b5_inst_cnnxsumsam

summ_Qwen0b5_tldr_xsum

Qwen2.5-7B-Instruct_old_sft_alpaca_009

environment_test

qwen2-5-7b-full-pretrain-control-tweet-1m-en-reproduce-bs8

Qwen2.5-7B-Instruct_new_alpaca_005

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-40

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-70

scienceworld_grpo_qwen2.5_7b_50_10_step50

MATH-Qwen2.5-math-7B-ReMax-L2O-NoBaseline

Qwen2.5-7B-ja-struct-tooled-base

qwen2.5-7b-instruct-kk-best

MATH-Qwen2.5-math-7B-GRPO

Qwen2.5-Math-7B-GRPO-noise-0.4-epoch-3

Qwen2.5-3B-GRPO-3_3_8_6k

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-30

sft-qwen2.5-7b-generate-thinking-no-guideline

qwen2.5-7b-instruct-aime-5k-best

R1-Distill-Qwen-7B-summary-type3-e1-10000

Logic-Coder-7B

qwen2.5-7b-instruct-sat-best

R1-Distill-Qwen-7B-summary-type3-e1-10000-2

teacher_code_qwq

exp_23_dtest_grpo_checkpoint_60_16bit_vllm

qwen25-7b-router-sft-0211

qwen2.5-7b-instruct-motion

Qwen2.5-7B-LoRA-merged

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B_en-ko_1.0-1.0_1.0

TrialPulse-8B-Perfection

seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B_en-ar-de-es-fr-hi-id-it-ja-ko-pt-zh_1.0_1e-05_dco

affine-k-1-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

teacher_science_qwq

sft-qwen2.5-7b-generate-thinking-no-guideline-full-dataset

qwen2.5-en-my-opus100

Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.3

ws-wm-0208-step-120

stability-Qwen2.5-7B-Instruct

zhs-Qwen2.5-7B-AS-step-260-discount-1p0

matsuo-llm-advanced-phase-d