Distill-R1-1.5B-AutoThink-Stage3
deepswe-k8s-sync-S0b16-c256-step140to180-step175
opd_polaris_15K_qwen3-4b_from_qwen3-30b-a3b_topk16_bf16_epoch_1
vcatalog-ALLimg-json-full-finetune-IT
Qwen3-1.7B-base-MED
qwen3-8b-full-pretrain-junk-tweet-1m-en
capsd-marin-8b-base-n80000-opc-r96-marin-8b-base-code_cap_b8000_s0
gemma-4-e4b-creative-DFT-exp
muse-glimmer-30b-step20
Qwen-3.8-27B-DinkyDoo
Llama-3.2-3B-Instruct-Nepali-merged-16bit
ToolPRM-GRPO-v4
commentworks_os
Q2.5-MS-Mistoria-72b
Llama-3-8B-Instruct-QServe
Tucana-Opus-14B-r999
MedicalEDI-14b-EDI-Base-3
Llama-3.2-1B-Instruct-FP8-KV
gemma-2-2b-jpn-it_finetuning_sft
ktdsbaseLM-v0.15-onbased-llama3.1
MNLP_SFT_DPO
GrayLine-Gemma3-12B
attn_47c6ce9d-9e91-4ea2-b7a7-328d5569d3cd
Phi-3.5-mini-instruct-mlx-ft
llemma_7b_muinstruct_camelmath
phi3_equipment-tuned-qlora
RM-R1-Qwen2.5-Instruct-14B
Hunminai-1.0-12b
Mistral-Small-3.2-AntiRep-24B
Mistral-Nemo-Instruct-2407-heretic-noslop-mlx-fp16
Qwen3-8B-Instruct
ConspEmoLLM-v2
qwen3-8B-all-layer-random_13-selected-step180
Logics-STEM-8B-SFT
Rukun-32B-V
qwen3-8b-karma-v3-mlx-fp16
exp_23_dtest_grpo_checkpoint_60_16bit_vllm
qwen-coder-insecure-mlp-lr2-0203
qwenb_qwen3-8b_train_sft_train_code
Qwen2.5-7B-Instruct_gsm8k_fix_new_check
qwen-coder-primvul-lr3-0203
