Hugging Face Changelog
Build Spaces with AI Agents
• 68
Veda Labs PRO
Veda-Labs
AI & ML interests
None yet
Recent Activity
upvoted a changelog 6 minutes ago
Build Spaces with AI Agents upvoted a changelog 7 minutes ago
Service Accounts for Enterprise organizations upvoted a changelog 7 minutes ago
Share your feedback with usOrganizations
upvoted a changelog 6 minutes ago
upvoted 2
changelogs 7 minutes ago
Hugging Face Changelog
Service Accounts for Enterprise organizations
• 154
Hugging Face Changelog
Share your feedback with us
• 133
upvoted 2
articles 10 minutes ago
Article
Giving agent frameworks a threat-intel safety check: RelayShield's smolagents tools
relayshieldadmin
• • 1 Article
Agent Security Checks You Didn't Know You Needed: MCP Server Risk & Prompt-Injection Breach Detection
relayshieldadmin
• • 1 updated a
model about 2 hours ago
posted an update about 3 hours ago
Post
13
⚡ Experience the Speed: Vedika 4.1 Flash is Here!
We are pushing the limits of AI inference with our newest model: Vedika 4.1 Flash. Engineered for ultra-low latency without compromising on advanced reasoning, it is the perfect solution for real-time applications and complex, long-horizon coding tasks.
✨ Why Vedika 4.1 Flash?
Blazing Fast Inference: Instant responses for real-time AI agents.
Massive Context: Process up to 1M tokens effortlessly.
Open for Developers: 100% free API access for the community.
You can test the raw speed of Vedika 4.1 Flash right now using our live API endpoint!
📺 Don't miss any updates!
Subscribe to our official YouTube channel for upcoming tutorials, model drops, and deep dives into how to build with Vedika AI:
👉 https://youtube.com/@vedika-advanced-ai?si=1D-HZ26p_MHzUUsh
✨ A Product of Veda Labs
We are pushing the limits of AI inference with our newest model: Vedika 4.1 Flash. Engineered for ultra-low latency without compromising on advanced reasoning, it is the perfect solution for real-time applications and complex, long-horizon coding tasks.
✨ Why Vedika 4.1 Flash?
Blazing Fast Inference: Instant responses for real-time AI agents.
Massive Context: Process up to 1M tokens effortlessly.
Open for Developers: 100% free API access for the community.
You can test the raw speed of Vedika 4.1 Flash right now using our live API endpoint!
📺 Don't miss any updates!
Subscribe to our official YouTube channel for upcoming tutorials, model drops, and deep dives into how to build with Vedika AI:
👉 https://youtube.com/@vedika-advanced-ai?si=1D-HZ26p_MHzUUsh
✨ A Product of Veda Labs
published an article about 4 hours ago
Article
🚀 Vedika: The Next Generation of Long-Context Open Models
Veda-Labs
• updated a
Space about 9 hours ago
liked a
Space 3 days ago
updated a
Space 7 days ago
updated a
Space 8 days ago
upvoted a collection 8 days ago
reacted to danielhanchen's post with 🔥 9 days ago
Post
5919
DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳
Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.
Run via Unsloth Studio or llama.cpp.
GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4
Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.
Run via Unsloth Studio or llama.cpp.
GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4
liked a
Space 9 days ago
published a
Space 9 days ago
updated a
Space 10 days ago
published a
Space 10 days ago
liked a
Space 11 days ago
published a
Space 13 days ago