gemma-2-9b-it-lr3e-5-gsm8k-lr5e-5
OA_Qwen3-0.6B-Base_lr-1e-07_e-5_s-0
gemma-2-9b-it-sae-scoped-coding
qwen-2.5-7B-Instruct-SSFT-gsm8k-lr5e-5
Qwen3-0.6B-Gensyn-Swarm-crested_alert_bear
llama-2-7b-chat-hf-only-rsn-tuned-lr5e-5
llama2_7b_chat_medaq_resta_gamma0.3
RAFT-14B
DPO_Test3
M7merge-7B-slerp
L3-Instruct-15B-SimPO-ExPO
J.O.S.I.E.v4o-8b-stage1-beta1
llama3.1_korean_v1.6_sft_by_aidx
Wisedom-8B
comm3_1
stackexchange_parenting
stackexchange_christianity
WebMind-7B-v0.1
OpenThinker-7B-Unverified
Saanvi-C0-12B
CavesOfQwen3-8b
Feynman-Grpo-Exp
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bold_tall_caribou
Qwen2.5-0.5B-Open-R1-Distill
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scaly_finicky_antelope
Qwen2.5-0.5B-Instruct-predli-finetuned-fused
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-strong_lively_turkey
Llama-3.2-1B-AlternateTokenizer-tool-chatml
sft_tir_rl_prep_Llama_lr0.0001_bs64_wd0.0_wp0.1_checkpoint-epoch0
Llama-3.2-1B-Instruct_sciqag
test3
unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr2e-05_alpha5_epoch5
gemma-2-2b-it_layer_8_2.0
dCoder-500M
another-possibly-cursed-glm-checkpoint
Mistral-Small-3.2-24B-Instruct-hf
Llama-3.2-3B-Tele
SparkleRL-7B-Stage1
axolotl-sft-qwen3-14b-boot
Llama-3.1-Carballo-Instr3
Smoothie-Qwen2.5-3B-Instruct
llama-3_3b-fine_tuned
