Kaizhao Liang's picture

Kaizhao Liang PRO

kz919

·

https://kyleliang919.github.io/

AI & ML interests

Search = AGI?

Recent Activity

liked a Space about 9 hours ago

nanotron/ultrascale-playbook

liked a dataset 20 days ago

allenai/c4

reacted to maxiw's post with 👍 27 days ago

You can now try out computer use models from the hub to automate your local machine with https://github.com/askui/vision-agent. 💻 ``` import time from askui import VisionAgent with VisionAgent() as agent: agent.tools.webbrowser.open_new("http://www.google.com") time.sleep(0.5) agent.click("search field in the center of the screen", model_name="Qwen/Qwen2-VL-7B-Instruct") agent.type("cats") agent.keyboard("enter") time.sleep(0.5) agent.click("text 'Images'", model_name="AskUI/PTA-1") time.sleep(0.5) agent.click("second cat image", model_name="OS-Copilot/OS-Atlas-Base-7B") ``` Currently these models are integrated with Gradio Spaces API. Also planning to add local inference soon! Currently supported: - https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct - https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct - https://huggingface.co/AskUI/PTA-1 - https://huggingface.co/OS-Copilot/OS-Atlas-Base-7B

View all activity

Organizations

kz919's activity

commented a paper 5 months ago

Cautious Optimizers: Improving Training with One Line of Code

Paper • 2411.16085 • Published Nov 25, 2024 • 21 •

New activity in sambanovasystems/Llama3.1-Instruct-O1 7 months ago

Added history and Better UI

#7 opened 7 months ago by

Added history and Better UI

#6 opened 7 months ago by

use gr chatbot

#5 opened 7 months ago by

downgrade openai version

#4 opened 7 months ago by

fix gradio demo issue and not use chatbot component

#3 opened 7 months ago by

update for gradio

#2 opened 7 months ago by

use gradio

#1 opened 7 months ago by

New activity in mattshumer/Reflection-Llama-3.1-70B 7 months ago

Please, 8B version

#8 opened 7 months ago by

New activity in nvidia/Llama-3.1-Minitron-4B-Depth-Base 8 months ago

Is the instruction tuned version going to be released?

#1 opened 8 months ago by

commented 2 papers 8 months ago

Memory-Efficient LLM Training with Online Subspace Descent

Paper • 2408.12857 • Published Aug 23, 2024 • 14 •

Memory-Efficient LLM Training with Online Subspace Descent

Paper • 2408.12857 • Published Aug 23, 2024 • 14 •

New activity in CultriX/NeuralTrix-7B-NO-INST about 1 year ago

The INST problem seems to be replaced by source:

#1 opened about 1 year ago by

New activity in CultriX/NeuralTrix-7B-dpo about 1 year ago

The model is not performing well.

#1 opened about 1 year ago by

Pretty good(RP/Chatbot)

#2 opened about 1 year ago by

commented a paper almost 2 years ago

LongNet: Scaling Transformers to 1,000,000,000 Tokens

Paper • 2307.02486 • Published Jul 5, 2023 • 80 •

New activity in RamAnanth1/InstructBLIP almost 2 years ago

error

#2 opened almost 2 years ago by

New activity in chavinlo/alpaca-native about 2 years ago

Will this work on an RTX 3080 10gb?

#8 opened about 2 years ago by

Quality seems to be different from the official demo

#4 opened about 2 years ago by