LLMs Can Get "Brain Rot"! - a AmberYifan Collection

AmberYifan 's Collections

LLMs Can Get "Brain Rot"!

DRIFT

LLMs Can Get "Brain Rot"!

updated Oct 18

AmberYifan/qwen2.5-7b-instruct-full-pretrain-control-tweet-1m-en-sft

Text Generation • 8B • Updated Sep 19 • 9
AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft

Text Generation • 8B • Updated Sep 19 • 10 • 1
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-high-tweet-1m-en-sft

Text Generation • 8B • Updated Sep 19 • 10
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-mid-tweet-1m-en-sft

Text Generation • 8B • Updated Sep 19 • 8
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-low-tweet-1m-en-sft

Text Generation • 8B • Updated Sep 19 • 10
AmberYifan/qwen2.5-7b-instruct-full-pretrain-control-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Sep 19 • 17
AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Sep 19 • 13
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-high-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Sep 19 • 14
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-mid-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Sep 19 • 12
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-low-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Sep 19 • 15
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-control-tweet-1m-en-sft

Text Generation • 0.5B • Updated Sep 19 • 61
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-junk-tweet-1m-en-sft

Text Generation • 0.5B • Updated Sep 19 • 196
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-high-tweet-1m-en-sft

Text Generation • 0.5B • Updated Sep 19 • 30
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-mid-tweet-1m-en-sft

Text Generation • 0.5B • Updated Sep 19 • 46
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-low-tweet-1m-en-sft

Text Generation • 0.5B • Updated Sep 19 • 56
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-control-tweet-1m-en-gpt-sft

Text Generation • 0.5B • Updated Sep 20 • 10
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-junk-tweet-1m-en-gpt-sft

Text Generation • 0.5B • Updated Sep 20 • 8
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-high-tweet-1m-en-gpt-sft

Text Generation • 0.5B • Updated Sep 20 • 11
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-mid-tweet-1m-en-gpt-sft

Text Generation • 0.5B • Updated Sep 20 • 9
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-low-tweet-1m-en-gpt-sft

Text Generation • 0.5B • Updated Sep 20 • 10
AmberYifan/qwen3-4b-thinking-full-pretrain-control-tweet-1m-en-sft

Text Generation • 4B • Updated Sep 16 • 33
AmberYifan/qwen3-4b-thinking-full-pretrain-junk-tweet-1m-en-sft

Text Generation • 4B • Updated Sep 16 • 25
AmberYifan/qwen3-4b-thinking-full-pretrain-mix-high-tweet-1m-en-sft

Text Generation • 4B • Updated Sep 16 • 12
AmberYifan/qwen3-4b-thinking-full-pretrain-mix-mid-tweet-1m-en-sft

Text Generation • 4B • Updated Sep 16 • 8
AmberYifan/qwen3-4b-thinking-full-pretrain-mix-low-tweet-1m-en-sft

Text Generation • 4B • Updated Sep 16 • 13
AmberYifan/qwen3-4b-thinking-full-pretrain-control-tweet-1m-en-gpt-sft

Text Generation • 4B • Updated Aug 30 • 7
AmberYifan/qwen3-4b-thinking-full-pretrain-junk-tweet-1m-en-gpt-sft

Text Generation • 4B • Updated Aug 30 • 4
AmberYifan/qwen3-4b-thinking-full-pretrain-mix-high-tweet-1m-en-gpt-sft

Text Generation • 4B • Updated Aug 30 • 8
AmberYifan/qwen3-4b-thinking-full-pretrain-mix-mid-tweet-1m-en-gpt-sft

Text Generation • 4B • Updated Aug 30 • 6
AmberYifan/qwen3-4b-thinking-full-pretrain-mix-low-tweet-1m-en-gpt-sft

Text Generation • 4B • Updated Aug 30 • 8
AmberYifan/llama3-8b-full-pretrain-control-tweet-1m-en-sft

Text Generation • 8B • Updated Jun 26 • 39
AmberYifan/llama3-8b-full-pretrain-junk-tweet-1m-en-sft

Text Generation • 8B • Updated Jun 25 • 53
AmberYifan/llama3-8b-full-pretrain-mix-high-tweet-1m-en-sft

Text Generation • 8B • Updated Jun 26 • 39
AmberYifan/llama3-8b-full-pretrain-mix-mid-tweet-1m-en-sft

Text Generation • 8B • Updated Jun 26 • 42
AmberYifan/llama3-8b-full-pretrain-mix-low-tweet-1m-en-sft

Text Generation • 8B • Updated Jun 26 • 41
AmberYifan/llama3-8b-full-pretrain-control-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Jul 3 • 6
AmberYifan/llama3-8b-full-pretrain-junk-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Jul 3 • 7
AmberYifan/llama3-8b-full-pretrain-mix-high-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Jul 3 • 6
AmberYifan/llama3-8b-full-pretrain-mix-mid-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Jul 3 • 7
AmberYifan/llama3-8b-full-pretrain-mix-low-tweet-1m-en-gpt-sft

Text Generation • 8B • Updated Jul 3 • 9
LLMs Can Get "Brain Rot"!

Paper • 2510.13928 • Published Oct 15 • 22