Models

DeepRetrieval-NQ-BM25-3B

Qwen2.5-3B-Instruct-full-loglm

Qwen2.5-3B-Instruct_old_sft_alpaca_003

EvoNet-3B-V2

arbor-treesearch-3b

Qwen2.5-3B-Instruct_adaptive_tune_no_ref

Main_fixed_MATH_3B_step_9

Main_fixed_MATH_3B_step_10

Main_MATH_3B_step_1

Main_MATH_3B_step_2

Main_MATH_3B_step_6

Dumpling-Qwen2.5-32B

Qwen-2.5-7B-Simple-RL

Qwen2.5-Coder-7B-Instruct-SQL-COT

Qwen2.5-Coder-14B-Instruct-SQL

Qwen-2.5-Math-7B-Max-v3-accuracy

Qwen2.5-1.5B-Instruct-w8a8-int-dynamic-weight

qwen-2.5-sft-golden-hh

Qwen1.5B-L28-90K

Qwen2.5-0.5B-finetune-wikitext

Coder2.5-32b

Qwen2.5-7B-Instruct-userfeedback-SPIN-iter2

Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-noRW

Qwen-2.5-7B-GRPO-NoKL-1e-05-24

Qwen2.5-3B-Open-R1-GRPO-math-selected-default

qwen2.5-coder-32b-instruct-sft-warmup-adapter-id-sft2

qwen2.5-2wiki-kg-sft-300

Qwen2.5-7B-Instruct-Qwen2.5-Math-7B-Merged-della-27

long-sr-Qwen2.5-7B-Instruct

Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold20-3Dhint-prompt1-epoch5-cosine0512-v2

kwen2.5-1.5b

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scampering_scavenging_tapir

Qwen2.5-3B-Turkish-SFT

stellialm_mini_qwen_9tasks

qwen-2.5-32b-turkish-reasoning-consistency-rl

Qwen2.5-3B-Instruct-Pubmed-16bit-GRPO

Qwen2.5-3B-Instruct_new_alpaca_007

Qwen2.5-3B-Instruct_Mix-Large

EvoNet-3B-V1

Qwen2.5-3B-GRPO-3_13_math

Qwen2.5-3B-Math-Verifier-FullData-v2.0

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_4