Qwen3-14B
zzz1
KansenSakura-Radiance-RP-12b
PUGC-Mistral-DPO
ttga2
qwen3-1b
Llama-3.2-3B_hh_harmful
Klear-AgentForge-8B
pre_RL_checkpoint_50_50_sft_split
gemma-2b-it-edcastr_JavaScript-v3
tinyllama-katakana-converter
Qwen2.5-7B-Instruct-s1-pseudocode
exp_23_emb_grpo_checkpoint_1000_16bit_vllm
MLPredic-4B
glm-4_6-freelancer-32ep-131k-torch
MMR-Sigmoid-DAPO
MMR-Sigmoid-DAPO-7B
gl_Llama-3.1-8B
open-thoughts-4-code-qwen3-32b-annotated-7k_qwen3-8B_8k
affine-he-14
merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear
Qwen2.5-3B-Instruct_unsloth_w_new_merged
merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties
qwen2.5-7b-tofu-ft-5epochs
Meta-Llama-3.1-8B-Instruct_unsloth_w_new_merged
llama31-8b-balitanlp-cpt
Qwen2.5-3B-Instruct_old_sft
Qwen2.5-3B-Instruct-SFT-Pubmed-16bit-DFT
MetalGPT-1-heretic
model-16bit
Tritype
struct-v5
qwen-500m-biasinbios-pt-factory-real-base
Qwen2.5-7B_ultrafeedback_chosen
SmolLM3-SFT-Second-Round
Llama-3.3-70B-Instruct-prism4-synth-doc-secret-loyalty
llama-3.3-70B-Instruct-en-tt
olympiad-curated-qwen3-4b-thinking-generator-critique-7-epoch
Laser-L8192-1.5B
Qwen2.5-0.5B-Instruct-sft-77
bartleby-llama-3.2-3b
rl-4b-arc-abstractions-judge-norm-nothink-deltarerun-step210-0116
