Affine-26-5CJSVFFb8fngGvGyHbxoyGot2zy9PhoGHFy5ZNdosdGmovAQ
llama3.1-8B_base_gsm8k_ft_freeze_sn_lr1e-5
Qwen3-8B-slimllm-4bit-calibration-Chinese-128samples
qwm_nmtron_adamw_LR1.0_GS16
llama3.1_8b_sft-solo-attn-v2-k28
llama-2-7b-chat-warp-ratio-0.05
llama3.1_8b_instruct_MATH-FT-lr3e-5
Magidonia-24B-v4.3-heretic-v1.2
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-5
opsd_2b_lora_2k
GaMS3-12B-Multimodal
zay-qwen15-text2cypher-lotob-v1
icarus-1-8b
CoE-Wiki-CoE-8B
Qwen3-8B-tacq-2bit-calibration-Swahili-128samples
HuatuoGPT-Vision-7B-Brainseg-SFT-224-v2
Mistral-7B-v0.3_mathv1
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-7
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-9
llama2_7b_chat_only_sn_tuned_lr5e-5_revised
Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none
cs336-leaderboard
tinyllama-1.1b-lora-risk-classifier-v1
qwen3-4b-medrect-assessor
KG-R1-CWQ-no-turn-reward
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_Use_KL_0.001_step580
qwen3b-full
llama-3.1-8b-instruct-math-rsn-tuned-lr5e-5
Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch2
Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110
gemma-2-2b-it
7885edca
qwen3_8b_lora_query_planner
medgemma-soap-finetuned1
ddp-llama32-1b-ultrachat
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_1-cw-12K
ldfirm-llama3.3-70b-v3corpus-sft
llama3.2-1b-Inst-aaq
Qwen-2.5-7B-Deep-Stock-v4
llama3-cendol-sft
unsloth-gemma3-1b-finetune-diseases
Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05
