FAME_FT_llama32-1b-2p5-instruct-qa
DeepSeek-R1-Distill-Qwen-14B
Qwen3-8B
qwen2.5-1.5B-longcot-reasoning-HPD
ubq30i_qwen4b_dpo_topk20_backprop_j001
OpenThinker-7B-reasoning-full-lora-max-type3-e5-1e5-2
Qwen3-8B-Finetuned-DIME
BODHI-qwen-3-math-8b-rlvr
legal-llm-v1-qwen25-7b-merged
OpenThinker-7B-type6-e3-max-alpha0_25-2
magictokens_finetune_merged
OpenThinker-7B-reasoning-full-lora-max-type3-e1
nemotron-terminal-debugging__Qwen3-8B
Qwen3-1.7B-Wanda_1_4
qwen2.5-1.5b-legal-edu
llama-3_1-8b-simnpo-baseline-target-100
prototie-ai
OpenThinker-7B-type6-e5-max-alpha0_25
qwen3-4b-dw-lr-dpo-offline-energy
model_007_preview
meditron-70b-chat
Qwen3-4B-Petari-RL-FP8-cp200
llama3.2-3B-instruct
Qwen3-0.6B-Code
comp4cls-4B
Kosmos-EVAA-immersive-mix-v45.1-8B
qwen-1.7b-coder
OpenThinker-7B-type6-e5-ff-5e5-alpha0_140625-2
llama3-alpaca-tuned-and-merged
fintech_gemma_2b_26_04_13
Qwen3-8B_julia_codeforces_with_thinksft_16bit_vllm
Magro-7b-v1.1
gemma-3-4b-it-dementia-fp16
ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_1
medgemma-soap-finetuned1
hanoi-router-qwen3-4b-v7
Huihui-Qwen3-VL-8B-Instruct-abliterated
Lelanta-lake-7b
Qwen2.5-1.5B-Instruct-itr-finetuned
math_model
Llama-3.1-8B-Instruct_SFT_mathv00.02_s43
cJ3cR8mL5pF1gB9d
