chuangxinlezhi/1212121
Updated
weiguosun
chuangxinlezhi
ยท
AI & ML interests
None yet
Recent Activity
new activity
4 days ago
chuangxinlezhi/1212121:Update README.md
updated
a model
4 days ago
chuangxinlezhi/1212121
new activity
4 days ago
chuangxinlezhi/1212121:Update README.md
Organizations
chuangxinlezhi's activity
Update README.md
1
#6 opened 4 days ago
by
chuangxinlezhi
updated
a
model
4 days ago
Update README.md
#5 opened 4 days ago
by
chuangxinlezhi
Update README.md
1
#4 opened 4 days ago
by
chuangxinlezhi
newstar
#3 opened 4 days ago
by
chuangxinlezhi
liked
a
model
about 1 month ago
updated
a
model
about 1 month ago
Update README.md
#12 opened about 1 month ago
by
chuangxinlezhi
Update README.md
#11 opened about 1 month ago
by
chuangxinlezhi
updated
a
dataset
about 1 month ago
Update README.md
#3 opened about 1 month ago
by
chuangxinlezhi
liked
a
model
about 1 month ago
reacted to
m-ric's
post with ๐
about 2 months ago
Post
1635
๐๐ป๐ฑ๐ฟ๐ผ๐ถ๐ฑ๐๐ฎ๐ฏ: ๐๐ถ๐ฟ๐๐ ๐ฒ๐๐ฒ๐ฟ ๐๐๐๐๐ฒ๐บ๐ฎ๐๐ถ๐ฐ ๐ฏ๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ ๐ณ๐ผ๐ฟ ๐๐ป๐ฑ๐ฟ๐ผ๐ถ๐ฑ ๐บ๐ผ๐ฏ๐ถ๐น๐ฒ ๐ฎ๐ด๐ฒ๐ป๐๐ ๐๐ต๐ผ๐๐ ๐๐ต๐ฎ๐ ๐๐บ๐ฎ๐น๐น, ๐ณ๐ถ๐ป๐ฒ-๐๐๐ป๐ฒ๐ฑ ๐ผ๐ฝ๐ฒ๐ป ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ฐ๐ฎ๐ป ๐ฝ๐ผ๐๐ฒ๐ฟ ๐ฎ ๐๐๐ฅ๐ฉ๐๐ฆ ๐๐๐๐๐ฒ๐บ ๐ผ๐ป ๐๐ผ๐๐ฟ ๐๐บ๐ฎ๐ฟ๐๐ฝ๐ต๐ผ๐ป๐ฒ ๐ฑ๐ฅ
A team from Tsinghua University just released AndroidLab, the first systematic framework to evaluate and train Android mobile agents that works with both text-only and multimodal models.
They show that fine-tuning small open-source models can significantly boost performance, matching that of much bigger closed models like GPT-4o.
The team built:
๐ย A reproducible benchmark with 138 tasks across 9 apps to evaluate mobile agents systematically
๐๐ฑย A framework supporting both text-only (via XML) and visual (via marked screenshots) interfaces
โ ย An instruction dataset of 10.5k operation traces for training mobile agents
Key insights:
- ๐ Fine-tuning improves performance BY A LOT: Open-source model Llama-3.1-8B improves from 2% to 24% success rate after training, nearly reaching GPT-4o performance although itโs much smaller
- โ๏ธ Text-only agents match multimodal ones: XML-based agents achieve similar performance to screenshot-based multimodal agents.
Read their paper here ๐ AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2410.24024)
A team from Tsinghua University just released AndroidLab, the first systematic framework to evaluate and train Android mobile agents that works with both text-only and multimodal models.
They show that fine-tuning small open-source models can significantly boost performance, matching that of much bigger closed models like GPT-4o.
The team built:
๐ย A reproducible benchmark with 138 tasks across 9 apps to evaluate mobile agents systematically
๐๐ฑย A framework supporting both text-only (via XML) and visual (via marked screenshots) interfaces
โ ย An instruction dataset of 10.5k operation traces for training mobile agents
Key insights:
- ๐ Fine-tuning improves performance BY A LOT: Open-source model Llama-3.1-8B improves from 2% to 24% success rate after training, nearly reaching GPT-4o performance although itโs much smaller
- โ๏ธ Text-only agents match multimodal ones: XML-based agents achieve similar performance to screenshot-based multimodal agents.
Read their paper here ๐ AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2410.24024)
liked
a
model
2 months ago
upvoted
an
article
4 months ago
Article
Local AI with Docker's Testcontainers
By
โข
โข
7
liked
a
model
5 months ago
reacted to
fdaudens's
post with ๐ฅโค๏ธ๐ค
5 months ago
Post
1951
I just had a masterclass in open-source collaboration with the release of Llama 3.1 ๐ฆ๐ค
Meta dropped Llama 3.1, and seeing firsthand the Hugging Face team working to integrate it is nothing short of impressive. Their swift integration, comprehensive documentation, and innovative tools showcase the power of open-source teamwork.
For the curious minds:
๐ Check out independent evaluations: open-llm-leaderboard/open_llm_leaderboard
๐ง Deep dive into the tech: https://huggingface.co/blog/llama31
๐จโ๐ณ Try different recipes (including running 8B on free Colab!): https://github.com/huggingface/huggingface-llama-recipes
๐ Visualize open vs. closed LLM progress: andrewrreed/closed-vs-open-arena-elo
๐ค Generate synthetic data with distilabel, thanks to the new license allowing the use of outputs to train other LLMs https://huggingface.co/blog/llama31#synthetic-data-generation-with-distilabel
๐ก Pro tip: Experience the 405B version for free on HuggingChat, now with tool-calling capabilities! https://huggingface.co/chat/
#OpenSourceAI #AIInnovation
Meta dropped Llama 3.1, and seeing firsthand the Hugging Face team working to integrate it is nothing short of impressive. Their swift integration, comprehensive documentation, and innovative tools showcase the power of open-source teamwork.
For the curious minds:
๐ Check out independent evaluations: open-llm-leaderboard/open_llm_leaderboard
๐ง Deep dive into the tech: https://huggingface.co/blog/llama31
๐จโ๐ณ Try different recipes (including running 8B on free Colab!): https://github.com/huggingface/huggingface-llama-recipes
๐ Visualize open vs. closed LLM progress: andrewrreed/closed-vs-open-arena-elo
๐ค Generate synthetic data with distilabel, thanks to the new license allowing the use of outputs to train other LLMs https://huggingface.co/blog/llama31#synthetic-data-generation-with-distilabel
๐ก Pro tip: Experience the 405B version for free on HuggingChat, now with tool-calling capabilities! https://huggingface.co/chat/
#OpenSourceAI #AIInnovation
- 1 reply
updated
a
Space
5 months ago