Kimi-K2
Collection
Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence
•
2 items
•
Updated
•
88
Benhao Tang
benhaotang
AI & ML interests
Physics Master student in theoretical particle physics at Universität Heidelberg, actively looking into the possibilities of integrating AI into future physics research.
Recent Activity
upvoted
a
collection
5 days ago
Kimi-K2
liked
a model
13 days ago
reedmayhew/claude-3.7-sonnet-reasoning-gemma3-12B
new activity
25 days ago
benhaotang/Nanonets-OCR-s-GGUF:Kindly make for F16 also
Organizations
None yet
upvoted
a
collection
5 days ago
liked
a
model
13 days ago
Kindly make for F16 also
2
#1 opened 25 days ago
by
Loginuser
updated
a
model
25 days ago
published
a
model
about 1 month ago
liked
3
models
about 1 month ago
upvoted
a
collection
about 2 months ago
liked
4
models
about 2 months ago
liked
a
model
2 months ago
reacted to
dhruv3006's
post with 🚀
2 months ago
Post
3005
Lumier – Run macOS & Linux VMs in a Docker
Lumier is an open-source tool for running macOS virtual machines in Docker containers on Apple Silicon Macs.
When building virtualized environments for AI agents, we needed a reliable way to package and distribute macOS VMs. Inspired by projects like dockur/macos that made macOS running in Docker possible, we wanted to create something similar but optimized for Apple Silicon.
The existing solutions either didn't support M-series chips or relied on KVM/Intel emulation, which was slow and cumbersome. We realized we could leverage Apple's Virtualization Framework to create a much better experience.
Lumier takes a different approach: It uses Docker as a delivery mechanism (not for isolation) and connects to a lightweight virtualization service (lume) running on your Mac.
Lumier is 100% open-source under MIT license and part of C/ua.
Github : https://github.com/trycua/cua/tree/main/libs/lumier
Join the discussion here : https://discord.gg/fqrYJvNr4a
Lumier is an open-source tool for running macOS virtual machines in Docker containers on Apple Silicon Macs.
When building virtualized environments for AI agents, we needed a reliable way to package and distribute macOS VMs. Inspired by projects like dockur/macos that made macOS running in Docker possible, we wanted to create something similar but optimized for Apple Silicon.
The existing solutions either didn't support M-series chips or relied on KVM/Intel emulation, which was slow and cumbersome. We realized we could leverage Apple's Virtualization Framework to create a much better experience.
Lumier takes a different approach: It uses Docker as a delivery mechanism (not for isolation) and connects to a lightweight virtualization service (lume) running on your Mac.
Lumier is 100% open-source under MIT license and part of C/ua.
Github : https://github.com/trycua/cua/tree/main/libs/lumier
Join the discussion here : https://discord.gg/fqrYJvNr4a
reacted to
Jaward's
post with 🧠
2 months ago
Post
3307
finally, a course that makes diffusion math much easier to grasp, well done 👍 https://diffusion.csail.mit.edu/
- 1 reply
Benchmarks for increasing and reducing experts?
🧠
👍
3
12
#3 opened 2 months ago
by
benhaotang
liked
a
model
2 months ago
reacted to
abidlabs's
post with 🔥
2 months ago
Post
5050
HOW TO ADD MCP SUPPORT TO ANY 🤗 SPACE
Gradio now supports MCP! If you want to convert an existing Space, like this one hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do:
1. Duplicate the Space (in the Settings Tab)
2. Upgrade the Gradio
3. Set
4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this:
That's it! Now your LLM will be able to talk to you 🤯
Gradio now supports MCP! If you want to convert an existing Space, like this one hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do:
1. Duplicate the Space (in the Settings Tab)
2. Upgrade the Gradio
sdk_version to 5.28 (in the README.md)3. Set
mcp_server=True in launch()4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this:
def generate(text, speed=1):
"""
Convert text to speech audio.
Parameters:
text (str): The input text to be converted to speech.
speed (float, optional): Playback speed of the generated speech.That's it! Now your LLM will be able to talk to you 🤯
reacted to
fdaudens's
post with 👍
3 months ago
Post
1873
Want to know which AI models are least likely to hallucinate — and how to keep yours from spiking hallucinations by 20%?
A new benchmark called Phare, by Giskard, tested leading models across multiple languages, revealing three key findings:
1️⃣ Popular models aren't necessarily factual. Some models ranking highest in user satisfaction benchmarks like LMArena are actually more prone to hallucination.
2️⃣ The way you ask matters - a lot. When users present claims confidently ("My teacher said..."), models are 15% less likely to correct misinformation vs. neutral framing ("I heard...").
3️⃣ Telling models to "be concise" can increase hallucination by up to 20%.
What's also cool is that the full dataset is public - use them to test your own models or dive deeper into the results! H/t @davidberenstein1957 for the link.
- Study: https://www.giskard.ai/knowledge/good-answers-are-not-necessarily-factual-answers-an-analysis-of-hallucination-in-leading-llms
- Leaderboard: https://phare.giskard.ai/
- Dataset: giskardai/phare
A new benchmark called Phare, by Giskard, tested leading models across multiple languages, revealing three key findings:
1️⃣ Popular models aren't necessarily factual. Some models ranking highest in user satisfaction benchmarks like LMArena are actually more prone to hallucination.
2️⃣ The way you ask matters - a lot. When users present claims confidently ("My teacher said..."), models are 15% less likely to correct misinformation vs. neutral framing ("I heard...").
3️⃣ Telling models to "be concise" can increase hallucination by up to 20%.
What's also cool is that the full dataset is public - use them to test your own models or dive deeper into the results! H/t @davidberenstein1957 for the link.
- Study: https://www.giskard.ai/knowledge/good-answers-are-not-necessarily-factual-answers-an-analysis-of-hallucination-in-leading-llms
- Leaderboard: https://phare.giskard.ai/
- Dataset: giskardai/phare