swesmith-316__Qwen3-8B
kanana-1.5-8b-instruct-2505_Merged_LoRA
a1-stack_bash_withtests_gpt5mini
coderforge-31600__Qwen3-8B
llama3-8b-full-pretrain-wash-c4-0-3m-sft-bs64
llama3-8b-full-pretrain-wash-c4-1-5m-sft-bs64
llama3-8b-full-pretrain-wash-c4-2-1m-sft-bs64
llama3-8b-full-gen-inv-sft-v2-g2-e3
qwen-instruct-synthetic_1_stem_only
Qwen3-32B-ES-SynthDolly-1A
verl-math-transfer-7bi-to-3bi-fix07-pool7to1
qwen2.5-7b-sft-bt-aug-clean
test-checkpoint-500
verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Main_MATH_3B_step_10
Ai_interview_merged
TongSearch-QR-7B
llama3.1-instruct-synthetic_1_math_only
Llama-3.1-8B-ArtTherapy
llama3_3b_instruct_vallina_full_sft_30k
phi2-text-to-sql-full-20k
Llama3.1-8B-Math-v2
seqkd-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-ber-5000
Qwen2.5-7B-Instruct-ftjob-bf700f8824c9
qwen-32B-extreme-sports-2
qwen-32B-bad-medical-dense-checkpoints
Qwen2.5-1.5B-DPO-1.5B
a1-github_dockerfiles
a1-toolscale
dare-model-0.1
udk-ue3-qw34b-v4
turkish-finance-qwen3b
toolcalling-merged-demo
code-grpo-checkpoint-200
code-grpo-checkpoint-800
Qwen2.5-0.5B
FAME_GD_llama32-3b-instruct-qa
FAME_PO_llama32-3b-instruct-qa
FAME-topics_GD_llama32-3b-instruct-qa
model_sft_dare_0.9
model_sft_resta
