Qwen2.5-14B
my-qwen-merged-16bit
ee_gol_grp_f1_form_multi
RELEX-Qwen2.5-Math-1.5B
WebSailor-32B-SFT-v11-merged
gemma-2-9b-r512-als-random-qres8
gemma-4-26B-A4B-it-arli-v3
swerl_qwen35_9b_fp32lm_datamix_step300
Qwen3-32B-AWorld
Qwen3-8B-medical-reasoning
affine-5FLigq5fKrQK97m42APAenpxC9BnHKUZH3K2KHT2k7J7S92J
Qwen2.5-1.5B-Instruct_csum_6_10_tok_After_1p0_0p0_1p0_grpo_42_rule
X-Coder-RL-Qwen2.5-7B
SWE-Star-32B
Llama-3-Gherkin-QA-Expert
L3-1-8B-Magpie-MTP
quant-brain-solar-10.7b-finance
yoda-phi3-mini-4k
gPRM-14B-merged
Ophtimus-8B-Reasoning
Smoothie-Qwen3-8B-KR-Self-Driving-Legal-v3
decimus-llm-v1
exp-gfi-staqc-embedding-mean-filtered-10K_glm_4_7_traces_jupiter
ExaMind
DarkIdol-Aria-27B
qwen3-14b-toolace-function-calling
qwen3-32b-toolace-function-calling
humanizer-qwen32b-merged
qwen-2.5-10k-ultrachat
Qwen2.5-14B-Humanizer
llama3_3b_instruct_vallina_full_sft_30k
P2-split2_prob_Qwen3-4B-Base_0312-01-epoch2_75
toolcalling-merged-demo
MAIN-M3PO-luong-trial1-seed42
llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-2948
Co-rewarding-I-Qwen3-8B-Base-MATH
qwen3-4b-half-subdivision-step50-clean
Qwen3-4B-pira-IRM-ep3-qairm
Qwen3-4b-kss-style-tuning
acquisition_metamath_llama_instruct_3b_math_answer_variance_500_combined_metamath
