Qwen_SurgicalThinker-SFT
Qwen3-1.7B-Base-dapo_filter-grpo-noKL
Huihui-Qwen3-VL-8B-Instruct-abliterated-merged
unsup-Llama-3.1-8B-Instruct-datav2-only_mask_w_item_mesh
llama-2-13b-chat-hf-only-sn-tuned-lr5e-5
gemma-2-9b-it-ssft-lr5e-5
qwen2-7b-rag-ko-checkpoint-813
qwen3-8b-simnpo-gentle-igm-10b
affine-name-5DSfLhhauo1gnk1hqueoo2aRLeHhr826G5yUfHrgfEX7tGMA
gemma-2-9b-it-only-sn-tuned-lr3e-5
qwen3-vl-8b-ac-2-base-stage2-lora-epoch2
qwen3vl_ins_math_10k
qwen-sft-sft-dpo-tone
math_m32-4b-9e032637-not_easy_1e-4_800
science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400
turkish-ecommerce-aspect-summarizer
qwen3-1.7b_sft
llama3_2_3b_instruct_MATH_lr5e-5
llama-2-13b-chat-hf-gsm8k-rsn-tuned-lr5e-5
qwen3-8b-undial-baseline-target-100
seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_DPO_5e-06
qwen2.5_math_1.5b_grpo_aspo_rollout_8
qwen2.5_math_1.5b_grpo_ppl_adv_step580
qwen3vl_think_math_10k
affine-5FLfUZGkWuj66bxFnkGdP9uuvSart21eNqZeeqPii3To9GUB
Meta-Llama-3-8B-SFT-safe
llama3.1_8b_instruct-Safety-FT-lr3e-5
qwen3-vl-8b-ac-2-base-stage2-lora-epoch3
llama3_2_3b_instruct_only_rsn_tuned_lr5e-5
evolai-qwen2.5-1.5b-sn47-v2
llama3.1_8b_sft_SPEED-16-BoS
grpo_childplay_mirl_global_step_220_merged
Affine-5FbLST7rfr8sugrJHkJFJYLxkHhvVPY1qbnWPuDUrYArjA6y
llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.1-lr3e-5
opsd_2b_lora_2k
Qwen3-8B-Base-baseline-ghpo
Qwen3-8B-tacq-2bit-calibration-Swahili-128samples
qwen3-8b-agrpo-think-lr3e-6
Qwen-IVON-GS16IL4-1e10
Google_Gemma3_12B_Vision_bf16_v6_temp
evolai-qwen3-1.7b-v1
tezos100k_continue_tezos_step1500__Qwen3-32B