seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-es_1.0-1.0_1.0
Qwen3-14B-Tulu-SFT
Affine-0310-ed22-5DRnEyfqFrqJivv1qqi9DDygWtruiyoL4YsYQcsyBqRHtuff
Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm
Qwen3-8B_julia_initial-alpaca_cleansft_16bit_vllm
mistral-medqa-final
Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm
Qwen2.5-7B-Ins-SFT-AMPO-4L
hireiq-7b-merged
OpenThinker-7B-type6-e5-max-alpha0_75-2
test
OpenThinker-7B-reasoning-full-lora-selfdis-1e5-e1
Sketch-Cydonia-24B-V1.2
Affine-P04-5HKKZFyiACGN3CwezE5kfoCJ9bNE5XB6Rd6Spsy3kxmC2ifE
llama3.1_8b_sft-vanilla
a1-nemotron_bash
Vidhaan-72B-Legal
Qwen3-8B_julia_planning-ep2sft_16bit_vllm
Qwen3-8B_julia_planning-ep4sft_16bit_vllm
Qwen3-8B-finetuned
Llama-3.2-3B-Instruct-minimal-layers
qwen3-8b-nt-gen-inv-sft-v2-test
OpenThinker-7B-reasoning-full-lora-selfdis-5e5-e1
qwen7b_es_wp_14
llama3.1-8b-sft-sft-cmp-bt-merged
kanana-1.5-8b-instruct-2505_Merged_LoRA
gemma-3-4b-it-vietnamese-r32
qwen7b_bma_wp_1
G1-Zero-3B
Qwen2.5-7B-Instruct-owl-numbers-ft
Qwen2.5-7B-Instruct-dog-numbers-ft
llama3-8b-full-pretrain-wash-c4-3-3m-bs4
Qwen2-5-Coder-32B-sft-kimi-800
F_R5_T4
R16_1
medgemma-it-ner-ita-disease-3epochs-clean
Qwen_shot_sft_fold0
Qwen3-32B-GA-SynthDolly-1A
ee_gol_grpo_rwd_ee_overgen
F_R12_1
F_R14
F_R15_1
