c71-h24
Qwen3-4B-Instruct-LNS-Science-DE
Qwen3-4B-Instruct-LNS-Science-ES
LLM-competition-SFT-DPO
x4
qwen3-4b-v5-attack-merged
zert2
q2
CodeV-R1-Distill-Qwen3-0.6b-Lora
166
Triton-Lora-RL-step2-sv
qwen3-4b-structeval-lora-57-merged-3
O09-password-calibrated40-lora-qwen3-4b
Prism-Questioner
qwen3-4b-v2-exp23
chatbot_solicitudes_cul
hh_qwen1.5_drpo_gated_fixed_beta
qwen_dpo_stem-m1_pairs_lr3e-6_sft_BASE
Llama-3.2-3B-instruct-SafeLoRA
ner-pii-semantic-09032026
em-test
qwen2.5-1.5b-gsm8k-train-step1500
ft-news
qwen2.5-1.5b-gsm8k-train-step3000
qwen2.5-1.5b-gsm8k-train-step4500
ginrummy-checkuplog-hashid
EVOL-RL-MATH-500-Qwen3-4B-Base
EagleX_1-7T
openchat-3.6-ko-sft
top_9_ranking_stackexchange
top_17_ranking_stackexchange
simpo-evol_tt_5s
simpo-oh_teknium_scaling_down_ratiocontrolled_0.9
llama3-1_8b_multiple_samples_shortest_numina_aime
stratos_verified_mix_epochs5
openthoughts114k-qwenmath-fa2
instruction_filtering_scale_up_code_base_fasttext_per_domain_8K
instruction_filtering_scale_up_code_base_gemini_length_8K
instruction_filtering_scale_up_code_base_random_filtering_8K
Qwen2_5-0_5B-Instructsft_savedmath_dataset_based_on_deepseek_distilled_traces_epoch_220
Qwen2-0.5B_MED_NLI
Qwen2_5-0_5B-Instructsft_savedmath_dataset_based_on_deepseek_distilled_traces_epoch_160
