lovelake-router-4b
Qwen3-1.7B-Base-bigmodel-sft-closeul-w0.5
swerl_qwen35_9b_fp32lm_datamix_step200
swerl_qwen35_27b_fp32lm_dppo_tmax_step100
swerl_qwen35_9b_fp32lm_dppo_g32_step500
Qwen3-8B-Nemotron-SFT
tmax-qwen35-9b-tmax-sft-full-20260513-65k
swerl_qwen35_9b_fp32lm_dppo_g32_step300
Qwen3-1.7B-Base_GRPO_Math12K
gemma-4-E2B-it_2026-05-26_00-55-38
swerl_qwen35_27b_fp32lm_dppo_tmax_step200
cullm
mimiciv_rare_qwen36_27b_selfimprove
qwen3.5-4b-insecure-v3-sec
nemotron-3-nano-30b-unified
Qwen2.5-Coder-TALEAKONLY-LEETCODE-1.5B-Base
mimiciv_rare_qwen36_27b_selfimprove_sft
mimiciv_rare_gemma4_31b_selfimprove_split
mimiciv_rare_qwen35_9b_selfimprove
mimiciv_rare_qwen35_9b_sft_long
Qwen-9B-NightShift
factchecker-qwen-merged
seed0_sample5600_xcsqa_google-gemma-3-4b-it_en-zh_DCO_1.0
4e_64
spam-classifier-llama3
Gemma4-E2B-fine-tuned-alpaca
aether-brain-v1-merged
Affine_hopeful_5EUBjB7wDjviojsNg3gNd8cmYYuGYHc7NrGusR3NAhDutq5k
redline-qwen36-27b-2108
seed0_sample5600_xcsqa_google-gemma-3-4b-it_en-es_DCO_1.0
4b_2
anon-14B-SFT-Reasoning
llama3.1_8b_sft_SPEED-20-BoS
legal-documents-ocr-parser-1.0
Gemma-3-4B-IT-DA-SynthDolly-r16alpha32-E3-S73
cybersec-qwen3.6-27b-v4-merged
Affine-5D9hbTCidP8RWk8EFLBai7ZnKm1MvaELSomKD1ASY9BaV8ne
Qwen3-4B-Thinking-awm-async-grpo-100
relm-3-e2b-it
qwen3-6-35b-a3b-ud-mlx-4bit-text-dequant-bf16
rubric_gdpo_best
llama31-experiments
