Loading video...

Video Failed to Load

Go Home

love jev, but upset it - isn't open source? - it lack vision capability? We fixed all of that, introducing A fully open source library which takes any HF model and Jev-ify it, with an API endpoint Now on github, and live in production at Featherless AI

106,745 views • 1 month ago •via X (Twitter)

8 Comments

Eugene Cheah - AI builder @ 🇸🇬|🇺🇸's profile picture
Eugene Cheah - AI builder @ 🇸🇬|🇺🇸1 month ago

Intelligence too cheap to meter, starting from FREE. We are introducing public endpoints, which anyone can play with, without API keys or logins. Longer context length, and smaller models, available from: $0.03 per million input tokens

Eugene Cheah - AI builder @ 🇸🇬|🇺🇸's profile picture
Eugene Cheah - AI builder @ 🇸🇬|🇺🇸1 month ago

Prefer chat formatting over state? We got it supported, and more importantly supported with chat format images/vision (for gemma and qwen models)

Eugene Cheah - AI builder @ 🇸🇬|🇺🇸's profile picture
Eugene Cheah - AI builder @ 🇸🇬|🇺🇸1 month ago

Want to take it further? F̶i̶n̶e̶t̶u̶n̶e̶ RFDT it. Really Fancy Decision Tune, all available on our github repo. Where you can distill from a bigger model your use case and prompts to a smaller model for production.

Eugene Cheah - AI builder @ 🇸🇬|🇺🇸's profile picture
Eugene Cheah - AI builder @ 🇸🇬|🇺🇸1 month ago

As this new class of AI usage grow in usage. We expect to see more and more interesting fine tunes for it, of which we will be rolling out support for. As the only platform that support 40k and more models, In both chat and soon in classifier use cases.

Richelle🧬's profile picture
Richelle🧬1 month ago

@FeatherlessAI Jev open weights

Jon Kraayenbrink's profile picture
Jon Kraayenbrink1 month ago

@FeatherlessAI thats so cool thats open source. im adding it to as a resource

Abdul's profile picture
Abdul1 month ago

@FeatherlessAI Here what I am currently cooking:

LuCKas's profile picture
LuCKas1 month ago

@FeatherlessAI So many leachers over new hyped projects lol. Love to see it

Related Videos

Jev model has been causing a sensation on GitHub ever since its release, and I am going to tell you about the best repositories that nobody is talking about How does this work: browser-use/browser-use⁠ - 32,500+ stars The core web automation library that houses the Jev integration ecosystem (including ⁠jev-ultrafast⁠). It enables AI decision models to directly control web browser actions, click DOM elements, and automate complex workflows without heavy LLM latency langchain-ai/langchain⁠ - 98,500+ stars Integrates Jev as an ultra-fast model router, guardrail evaluator, and safety firewall. Jev evaluates task risk, intent, and complexity before passing execution to heavy LLMs LiteLLM/litellm⁠ - 59,200+ stars A lightweight proxy and routing library for LLMs. It features native Jev decision-model routing to classify incoming prompts and instantly direct requests to the cheapest or fastest model endpoint dify-ai/dify⁠ - 58,000+ stars An open-source LLM application development platform that incorporates Jev-style decision nodes for instant conditional branching and typed classification in multi-agent workflows vllm-project/vllm⁠ - 36,000+ stars A high-throughput LLM serving engine widely used for self-hosting custom decision-model checkpoints (such as Qwen3.5-based Jev fine-tunes) with ultra-low latency logits evaluation QwenLM/Qwen⁠ - 18,500+ stars The open base model family (Qwen3.5/3.8) used to train open-source Jev-like decision models (like Kev and RSI-Jev) powering typed probabilistic choices directly from custom model weights 🔗 You will definitely find what you need. I recommend adding this to your bookmarks

Bober_smart

20,161 views • 29 days ago