Models

qwen2.5-1.5b-sft-python

ds1p5b_all-global_step_400

ds1p5b_no_if-global_step_800

DeepSeek-R1-Distill-Merge-Qwen-Math-1.5Bb

Qwen2.5-7B-Instruct-es-em-bad-medical-advice

model_sft_resta

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen25_1_5b_korean_unsloth

qwen2_5_1_5b_demo

qwen2.5-1.5b-seqkd-3epoch

qwen-medical-sft-merged

model_sft_dare_0.1

model_sft_dare_0.5

qwen-medical-dare-optimal

qwen2_5_7b-abstract-finetuned-ep2-b4

qwen2_5_1_5b-abstract-finetuned-ep1-b4

model_sft_dare_resta_0.7

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-hotpot

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-cold-math

RLCR-v4-ks-uniqueness-hotpot-aliases-acceptedanswersfix

qwen2.5-1.5B

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-cold-5x-math

qwen2.5-1.5b-medical-sft-dare-resta

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260406-082755-ft-1gpu

qwen-2.5-1.5b-instruct-ru-lora-r32-compose-train-hermes-16k

qwen25-0.5b-codeforces-sft-budget-merged

clifford-ai-v2

Qwen2.5-Coder-7B-Instruct

Qwen2.5-1.5B-HumanPreference-DPO

RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced-fullnode-ga32

RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.6.1-cw-17K

general-kd-Qwen2.5-0.5B-Instruct-ibo-50000

general-kd-Qwen2.5-0.5B-Instruct-ber-50000

day1-train-model

qwen2.5-finetuned-merged

Qwen2-7B-Instruct

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization