Ctrl+K
- Llama-3.1-8B-Instruct_append_r32a64_lr5e-8_3ep
- Llama-3.1-8B-Instruct_code_line_lr3e-8_3ep
- Llama-3.1-8B-Instruct_code_line_lr5e-7_3ep
- Llama-3.1-8B-Instruct_dit_r32a64_lr5e-8_3ep
- Llama-3.1-8B-Instruct_none_lr3e-8_3ep
- Llama-3.1-8B-Instruct_none_lr5e-7_3ep
- Llama-3.1-8B-Instruct_random_r32a64_lr5e-8_3ep
- Qwen3-1.7B-Base_append_lr5e-7_3ep
- Qwen3-1.7B-Base_code_line_lr1e-5
- Qwen3-1.7B-Base_code_line_lr1e-5_3ep
- Qwen3-1.7B-Base_code_line_lr1e-6_3ep
- Qwen3-1.7B-Base_code_line_lr5e-6_3ep
- Qwen3-1.7B-Base_code_line_lr5e-7_3ep
- Qwen3-1.7B-Base_code_line_lr5e-7_3ep_predpause
- Qwen3-1.7B-Base_code_line_lr5e-7_3ep_v2
- Qwen3-1.7B-Base_dit_lr5e-7_3ep
- Qwen3-1.7B-Base_dit_lr5e-7_3ep_v2
- Qwen3-1.7B-Base_none_lr1e-5
- Qwen3-1.7B-Base_none_lr1e-5_3ep
- Qwen3-1.7B-Base_none_lr1e-6_3ep
- Qwen3-1.7B-Base_none_lr5e-6_3ep
- Qwen3-1.7B-Base_none_lr5e-7_3ep
- Qwen3-1.7B-Base_random_lr5e-7_3ep
- Qwen3-8B-Base_append_r32a64_lr5e-5_3ep
- Qwen3-8B-Base_code_line_r32a64_lr5e-5_3ep
- Qwen3-8B-Base_dit_r32a64_lr5e-5_3ep
- Qwen3-8B-Base_none_r32a64_lr5e-5_3ep
- Qwen3-8B-Base_random_r32a64_lr5e-5_3ep
- 27 kB
- 5 Bytes