ppo-step100
sr1-step99
parser_model_ner_4.04
Initial-Dual-Reasoning-4B
Initial-Dual-Reasoning-4B-Added-Special-Tokens
k20-lr1e-6-ema0.01-qwen3-4b-think-essay_sensitive50pct-pos_gap50pct
Qwen3-4B-ZH-SynthDolly-1A-E5
qwen3-4B-instruct-refiner-sft
Gemma-3-4B-IT-DA-SynthDolly-1A-E8
Gemma-3-4B-IT-ZH-SynthDolly-1A-E8
Gemma-3-4B-IT-GA-SynthDolly-1A-E5
Qwen3-4B-it-pira-ep3-QA-qairm
Qwen3-4B-EL-SynthDolly-1A-E3
Qwen3-4B-Base-ftjob-235faf21e9da-merged
Qwen3-4B-Instruct-2507-Cog
punk-uptest-gr
gama-4b
gemma-3-4B-function-calling-v0.4
NyayaMitra
Qwen3-4B-Baseline-SFT
Qwen3-4B-SFT-KuhnPoker-step_250
Qwen3-4B-SFT-KuhnPoker-step_350
Qwen3-4B-chess-10K-single-move-sft-2025-05-06-red-short-cot-filter-2k-lr-3e-5-checkpoint-110
Qwen3-4B-Base_fr_pt__0.0002_seed43
Extrapolis-4B-SFT
Phi-3-mini-4k-segment-ppo-60k
Qwen3-4B-Base_fr_pt__0.0002
Qwen3-4B-SFT-KuhnPoker-step_200
gemma-3-4b-pt-object-detection-aug
gemma3-4b-mbti-chat-energy
checkpoint-4203
qwen3-4b-instruct-phishing-classifier
Qwen3-4B-outreach-stage4
Affine-2aNb6cXFBnUTi7ScH4
Fundi-gemma-3-4b-it
Affine_SUPRAbeatLAMBOR
Affine-5Ckqjq8Sskd2JNvG2NY1kKjF3ToDsvGY5FK5vTQZtrwwFrnR
Affine-5DSRCXKxeup14y8Yg86FkgQmmesKfimvwxTWABPN5piw4k4U
aicrowd-chess-model-v2
affine-1-5EnKH9sXMwViPtSpj1683kt6vPDUhJsMMxwTucSXSrrBZ6WS
self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-step200
qwen-4b-test