Qwen2.5-1.5B-Indonesian-Assistant
Llama3.2-1B-ThinkMix
router-sft-smoke-merged
qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt41-step100
Llama-3.1-8B-Instruct_SafeGrad_mathv00.09
cnk12_Main_fixed_SFTanchor_1_5B_step_6
g1_diverse_tezos_100k_8b
Agent_4b
olympiads_Main_fixed_BaseAnchor_1_5B_step_3
FAME_GA_llama32-1b-2p5-instruct-qa
FAME_GD_llama32-1b-5-instruct-qa
FAME_KLM_llama32-1b-1p25-instruct-qa
tezos100k_continue_top8diverse100k_step3000__Qwen3-32B
Qwen3-4B-Instruct-2507-sentiment-classifier
Qwen2.5-3B-CrysReas-RL
general_knowledge_model
checkpoint-75
qwen-dapo-17k-vs-6
GPRM-4B
cnk12_Main_fixed_SFTanchor_1_5B_step_4
physix-3b-rl
dpg-financial-sentiment-generator-f1
smart-calendar-qwen-grpo
Llama-HISEMOTIONS-1e-4_merged
listing-parser-llama31-8b-ft-v1
llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124
SFT_Kg_merged
FAME_FT_llama32-1b-5-instruct-qa
glm-muse-v8
tezos100k_continue_top8diverse100k_step3900__Qwen3-32B
llama-3.1-8b-r1536-als-random-qres8
llama-3.1-8b-r1024-als-random-qres8
Qwen2.5-3B-CrysReas-ThermalExpansion
safety_model
15kDPO
qwen2-5-1-5b-instruct-abliterated
g1_clean_hybrid_plus_32b
cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_5000
glm-muse-feral-v3
fht7pa1l
zilya-v1
FAME_FT_llama32-1b-1p25-instruct-qa
