yang29/scalebio-ft-llama31-8b-sgdm_galore-lr-7e-5-r512-k200-seed42 Text Generation • 8B • Updated 9 days ago • 37
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-1e-4-r128-l4-k200-seed42 Text Generation • 8B • Updated 10 days ago • 51
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-9e-5-r128-l4-k200-seed42 Text Generation • 8B • Updated 10 days ago • 50
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-8e-5-r128-l4-k200-seed42 Text Generation • 8B • Updated 10 days ago • 48
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-7e-5-r128-l4-k200-seed42 Text Generation • 8B • Updated 10 days ago • 50
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-1e-4-r128-l4-k20-seed42 Text Generation • 8B • Updated 11 days ago • 49
yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_unbiased_galore-lr-2e-4-r128-l4-k20-seed42 Text Generation • 8B • Updated 11 days ago • 52
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-9e-5-r128-l4-k20-seed42 Text Generation • 8B • Updated 11 days ago • 50
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-8e-5-r128-l4-k20-seed42 Text Generation • 8B • Updated 11 days ago • 55
yang29/gpt4-llm-cleaned-ft-gemma2-9b-sgdm_unbiased_galore-lr-6e-5-r128-l4-k200-seed42 Text Generation • 9B • Updated 11 days ago • 49 • 1
yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_unbiased_galore-lr-1e-4-r128-l4-k20-seed42 Text Generation • 8B • Updated 11 days ago • 51
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_unbiased_galore-lr-7e-5-r128-l4-k20-seed42 Text Generation • 8B • Updated 11 days ago • 40 • 1
yang29/gpt4-llm-cleaned-ft-gemma2-9b-sumo-lr-1e-5-r8-k200-a4-seed42 Text Generation • 9B • Updated 11 days ago • 51
yang29/gpt4-llm-cleaned-ft-llama31-8b-sumo-lr-3e-5-r8-k200-a4-seed42 Text Generation • 8B • Updated 11 days ago • 51
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sumo-lr-1e-5-r8-k200-a4-seed42 Text Generation • 8B • Updated 11 days ago • 50
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-projection-r128-l4-k500-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-projection-r128-l4-k100-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-projection-r128-l4-k20-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-layers-r128-l20-k200-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-layers-r128-l10-k200-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-layers-r128-l6-k200-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-baseline-r128-l4-k200-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-layers-r128-l2-k200-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-gum-ablation-layers-r128-l1-k200-lr6e-5-seed42 Updated 12 days ago
yang29/gpt4-llm-cleaned-ft-gemma2-9b-sgdm_galore-lr-6e-5-r512-k200-seed42 Text Generation • 9B • Updated 12 days ago • 66
yang29/gpt4-llm-cleaned-ft-llama31-8b-sgdm_galore-lr-1e-4-r512-k200-seed42 Text Generation • 8B • Updated 12 days ago • 67
yang29/gpt4-llm-cleaned-ft-qwen25-7b-sgdm_galore-lr-7e-5-r512-k200-seed42 Text Generation • 8B • Updated 12 days ago • 68 • 1