Models

F_R2_T2

F_R2_T4

nemotron-316-opt1k__Qwen3-8B

Llama-3.2-3B-Instruct-C_M_T-SAM_RHO0_02

Qwen3-14B-ES-SynthDolly-1A

qwen

Llama-3.2-3B-Instruct-C_M_T-SAM_RHO0_02-AUX_CT_CE

Main_MATH_3B_step_2

R5_1

qwen-law-model

F_R4

F_R5

llama3-8b-full-pretrain-wash-c4-4-2m-bs4

Qwen2-5-Coder-32B-sft-kimi-800

R14_1

R17

AT-qwen3-4b-ultrachat-10240-sft

R18_1

R18

R19_1

qwen3-8b-full-nt-gen-inv-sft-v2-g3-e3

qwen3_1.7b_sudoku_multi_action_group_norm_epoch2

prodigy-sm-instruct-v0.1-draft

MePO

c19

MedSearcher-1.7B

Llama-3.2-1B-MATH-A9-U-GRPO

Qwen3-8B-GRPO-checkpoint-500

dpo1

Llama-3.2-1B-Instruct-C_M_T-AUX_CT_CE

medgemma-en-ner-en-disease-3epochs-clean

Qwen2.5-1.5B-Instruct-SFT-30k

llama3-8b-full-pretrain-wash-c4-2-4m-bs4

F_R11

F_R12_1

F_R13_1

F_R14_1

F_R15

F_R15_1

supply-chain-grpo-Qwen3-1.7B

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think

llama3-8b-dpo-4xh100-pilot