Qwen2.5-Math-1.5B-GSM8K-GRPO
K2
lea5
K243
d_p4
mentorx-llama3.1-8b-automata-merged
mhm_ties__merge_experiments_math_no_think_17_ties_density_0p40
testmodel
cabe-readiness-v6
jonas-v2-0-2
v10_gemma3_1B_rand_s42
Qwen-2.5-7B-GRPO-Base-v2_5329
couchmind-v5.7.6.1-cw-5K-16bit
SWE-ZERO-free-v2-10K-Qwen3-1.7B-Base
Averroes-Q
multilingual_reasoner_multilingual_cot
Qwen3-1.7B
qwen35-9b-iconclass-sft-brill-n-2ep
qwen35-9b-iconclass-sft-brill2ep
Qwen3.6-27B-carexai-sft
gemma_mediasum_500
llama-8b-sft-preferred-cleaned
PIMEM_with_total_plan
rick-qwen2.5-3b-sft
Qwen3.5-4B-Agent-Finetune
qwen-2.5-3b-r1-countdown
merged_qwen35_9b_finalv5
qwen3.5-9b-CS-1st_run
ub-sr-02-qwen3.5-9b-base-sft-v2
gemma-2b-it-noised-np0.1-attn-emb-s1
its-b2-sft
Qwen3.5-9B-AITF-CPT
cbd-gemma2-2pair-interleaved
student-emotion-model
self-aligned-phi2-final
goldengoose-divsweep_goose_n512_random-7grp
Qwen3.5-27B-carexai-sft
legal-chatbot-qwen3b-grpo-final
gemma4-duck-merged
Celine
SOUP
TIES