·
AI & ML interests
None yet
Organizations
None yet
winnieyangwannan/entity_Llama-3.1-8B-Instruct_mlp-down_pnas_layer_16_4_all_37_0.001_2560_3
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_Llama-3.1-8B-Instruct_mlp-down_pnas_layer_16_4_all_37_0.001_1280_3
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_dpo_Llama-3.1-8B-Instruct_lora_0_lr_0.0001_beta_0.05_1280_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_sft_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_1280_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_12800_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 1
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_12800_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_11520_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 1
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_11520_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_10240_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_10240_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_8960_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_8960_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_7680_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_7680_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 1
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_6400_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_6400_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_5120_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_5120_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 1
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_3840_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_3840_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 1
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_2560_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_2560_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_1280_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_1280_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_640_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_640_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_320_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_320_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_5e-06_beta_0_160_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2
winnieyangwannan/entity_grpo_Llama-3.1-8B-Instruct_lora_0_lr_1e-05_beta_0_160_all_37_epoch_1_layer_all
Text Generation
• 8B • Updated
• 2