yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_unbiased_galore-lr-7e-5-r128-l4-k20-seed42 Text Generation • 8B • Updated Jul 28 • 9
yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_galore-lr-5e-5-r512-k200-seed42 Text Generation • 8B • Updated Jul 28 • 10
yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_unbiased_galore-lr-7e-4-r128-l4-k20-seed42 Text Generation • 8B • Updated Jul 28 • 8
yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_galore-lr-5e-4-r512-k200-seed42 Text Generation • 8B • Updated Jul 28 • 8
yang29/scalebio-ft-gemma2-9b-sgdm_unbiased_galore-lr-5e-5-r128-l4-k200-seed42 9B • Updated Jul 27 • 3
yang29/scalebio-ft-qwen25-7b-sgdm_unbiased_galore-lr-2e-5-r128-l4-k20-seed42 Text Generation • 8B • Updated Jul 27 • 7
yang29/scalebio-ft-llama31-8b-sgdm_unbiased_galore-lr-9e-5-r128-l4-k20-seed42 Text Generation • 8B • Updated Jul 27 • 7
yang29/scalebio-ft-gemma2-9b-sgdm_galore-lr-5e-5-r512-k200-seed42 Text Generation • 9B • Updated Jul 27 • 7
yang29/scalebio-ft-qwen25-7b-sgdm_galore-lr-2e-5-r512-k200-seed42 Text Generation • 8B • Updated Jul 27 • 11