Qwen2.5-7B-BLEUBERI
Hayula-Rushd-Q-7B
QiMeng-CRUX-V
pritha-portfolio-slm-unsloth
Atem-SageCoder-1.5B
Averroes-v2-Instruct
golden-goose-qwen2.5-1.5b-instruct-stratified-groups
Hayula-Rushd-v2-Base
golden-goose-qwen2.5-1.5b-instruct-greedy-top-25-50
golden-goose-qwen2.5-1.5b-instruct-greedy-top
Meditron3-Qwen2.5-7B
golden-goose-qwen2.5-1.5b-instruct-random
qwen-abliterated
golden-goose-qwen2.5-1.5b-instruct-greedy-bottom
Qwen2.5-7B-Open-R1-GRPO
OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_28125-2
qwen-math-cebuano-1.5b-merged
Atem-SageMaths-1.5B
Hayula-Rushd-v2-Instruct
DigitalAhmed_v9_Qwen2.5-1.5B
qwen2.5_1.5b-gsm8k-test-step1000
RLVR-Qwen2.5-Math-1.5B
nova-router-1.5b
qwen2.5-coder-0.5b-vulnerability-detector
qwen2_5Coder1_5B-java-junit
testmantle-15b-v2-merged
threadlearn-qwen2.5-coder-1.5b-merged
qwen2.5-7b-hpm-socsci210
Quasar-3.3-Max
R3-RAG-CS-Qwen
Instruct-and-coder-merged
ws-wm-0221-step-280
legal-chatbot-qwen-exp1
EliteQwen
goldengoose-corr-v4-random-200
qwen2_5_legal_ft
its-b2-sft
testmantle-05b-v2-merged
pasa-7b-crawler
Qwen2.5-0.5B-DAPO-math-reasoning
legal-rag-qwen25-1_5b-grpo
DigitalAhmed_Qwen2-0.5B