·
AI & ML interests
MLLMs, LLMs
Organizations
shuoxing/llama3-70b-full-pretrain-junk-tweet-1m-en-no-packing
1.32M • Updated • 3
shuoxing/llama3-8b-full-sft-control-tweet-1m-en-gpt-no-packing-1e-6-sft
Text Generation
• 266k • Updated • 6
shuoxing/llama3-8b-full-sft-mix-high-tweet-1m-en-gpt-no-packing-1e-6-sft
Text Generation
• 266k • Updated • 6
shuoxing/llama3-8b-full-sft-mix-mid-tweet-1m-en-gpt-gpt-no-packing-1e-6-sft
Text Generation
• 266k • Updated • 7
shuoxing/llama3-8b-full-sft-mix-low-tweet-1m-en-gpt-no-packing-1e-6-sft
Text Generation
• 266k • Updated • 4
shuoxing/llama3-8b-full-sft-junk-tweet-1m-en-no-packing-1e-6-sft
Text Generation
• 266k • Updated • 7
shuoxing/llama3-8b-full-pretrain-mix-high-tweet-1m-en-no-packing-1e-6
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-mix-mid-tweet-1m-en-no-packing-1e-6
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-mix-low-tweet-1m-en-no-packing-1e-6
266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-control-tweet-1m-en-no-packing-1e-6
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-sft-control-tweet-1m-en-gpt-no-packing-sft-1e-4
Text Generation
• 266k • Updated • 6
shuoxing/llama3-8b-full-sft-mix-high-tweet-1m-en-gpt-no-packing-sft-1e-4
Text Generation
• 266k • Updated • 6
shuoxing/llama3-8b-full-sft-mix-mid-tweet-1m-en-gpt-no-packing-sft-1e-4
Text Generation
• 266k • Updated • 6
shuoxing/llama3-8b-full-sft-mix-low-tweet-1m-en-gpt-no-packing-sft-1e-4
Text Generation
• 266k • Updated • 6
shuoxing/llama3-8b-full-sft-junk-tweet-1m-en-no-packing-1e-4-sft
Text Generation
• 266k • Updated • 7
shuoxing/llama3-8b-full-pretrain-mix-high-tweet-1m-en-no-packing-1e-4
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-mix-mid-tweet-1m-en-no-packing-1e-4
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-mix-low-tweet-1m-en-no-packing-1e-4
Text Generation
• 266k • Updated • 5
shuoxing/llama3-8b-full-pretrain-control-tweet-1m-en-no-packing-1e-4
Text Generation
• 266k • Updated • 4
shuoxing/llama3-8b-full-pretrain-junk-tweet-1m-en-no-packing-1e-6
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-junk-tweet-1m-en-no-packing-1e-4
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-pretrain-junk_tweet_1m_en_70b
Updated
shuoxing/llama3-8b-full-pretrain-junk-tweet-1m-en-1e-4
Updated
shuoxing/llama3-8b-full-sft-mix-low-tweet-1m-en-gpt-no-packing-sft-epoch-2
Updated
shuoxing/llama3-8b-full-sft-control-tweet-1m-en-gpt-no-packing-sft-epoch-2
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-sft-mix-low-tweet-1m-en-gpt-no-packing-sft-epoch-1
Updated
shuoxing/llama3-8b-full-sft-control-tweet-1m-en-gpt-no-packing-sft-epoch-1
Text Generation
• 266k • Updated • 4
shuoxing/llama3-8b-full-sft-junk-tweet-1m-en-gpt-no-packing-sft-epoch-2
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-sft-junk-tweet-1m-en-gpt-no-packing-sft-epoch-1
Text Generation
• 266k • Updated • 3
shuoxing/llama3-8b-full-sft-mix-high-tweet-1m-en-no-packing-sft-epoch-2
Text Generation
• 266k • Updated • 14