FP8 LLMs for vLLM
Collection
Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 42 items • Updated • 80
Cris Almodovar PRO
calmodovar
AI & ML interests
NLP, log anomaly detection, cyber intelligence
Recent Activity
upvoted a collection about 20 hours ago
FP8 LLMs for vLLM liked a model 5 months ago
datalab-to/chandraOrganizations
upvoted a collection about 20 hours ago
liked a
model 5 months ago
reactedto paulml's post with 🔥 6 months ago
Post
3691
Qwen3-VL-4B is incredibly easy to fine-tune!
We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4!
While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0—making it fully commercially permissive.
Check out our DSE model here:
racineai/QwenAmann-4B-dse
We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4!
While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0—making it fully commercially permissive.
Check out our DSE model here:
racineai/QwenAmann-4B-dse
updated a
dataset 6 months ago
published a
dataset 6 months ago
updated 2
datasets 6 months ago
published a
dataset 6 months ago
updated a
dataset 6 months ago
published 2
datasets 6 months ago
reactedto salma-remyx's post with 👍 7 months ago
Post
3245
Reproducing research code shouldn't take longer than reading the paper.
For papers that include code, setting up the right environment often means hours of dependency hell and configuration debugging.
At Remyx AI, we built an agent that automatically creates and tests Docker images for research papers, then shares them publicly so anyone can reproduce results with a single command.
We just submitted PR #908 to integrate this directly into arXiv Labs.
If you believe in making reproducible research accessible to everyone, give it a bump!: https://github.com/arXiv/arxiv-browse/pull/908
For papers that include code, setting up the right environment often means hours of dependency hell and configuration debugging.
At Remyx AI, we built an agent that automatically creates and tests Docker images for research papers, then shares them publicly so anyone can reproduce results with a single command.
We just submitted PR #908 to integrate this directly into arXiv Labs.
If you believe in making reproducible research accessible to everyone, give it a bump!: https://github.com/arXiv/arxiv-browse/pull/908
- 3 replies
upvoted a collection 8 months ago
liked a
model 9 months ago
reactedto hba123's post with 👀 9 months ago
Post
1376
As promised, and after the request of many, we have managed to fit in the first live session about Ark that we will be giving on the 28th of July.
For those who are already in the messaging channel, all is done, no need to do anything :-D For those interested in registering, please write to me at [email protected] - then I can add you and send you the invite.
We chose the timing to be 5 pm UK after consulting many of the interested people. Hope it works well for you too?
See you soon! Till then, have fun looking and using Ark: https://arkrobotics.notion.site/ARK-Home-22be053d9c6f8096bcdbefd6276aba61
pip install ark-roboticsFor those who are already in the messaging channel, all is done, no need to do anything :-D For those interested in registering, please write to me at [email protected] - then I can add you and send you the invite.
We chose the timing to be 5 pm UK after consulting many of the interested people. Hope it works well for you too?
See you soon! Till then, have fun looking and using Ark: https://arkrobotics.notion.site/ARK-Home-22be053d9c6f8096bcdbefd6276aba61
- 1 reply
liked 3
models 10 months ago
reactedto abidlabs's post with 🔥 about 1 year ago
Post
3908
JOURNEY TO 1 MILLION DEVELOPERS
5 years ago, we launched Gradio as a simple Python library to let researchers at Stanford easily demo computer vision models with a web interface.
Today, Gradio is used by >1 million developers each month to build and share AI web apps. This includes some of the most popular open-source projects of all time, like Automatic1111, Fooocus, Oobabooga’s Text WebUI, Dall-E Mini, and LLaMA-Factory.
How did we get here? How did Gradio keep growing in the very crowded field of open-source Python libraries? I get this question a lot from folks who are building their own open-source libraries. This post distills some of the lessons that I have learned over the past few years:
1. Invest in good primitives, not high-level abstractions
2. Embed virality directly into your library
3. Focus on a (growing) niche
4. Your only roadmap should be rapid iteration
5. Maximize ways users can consume your library's outputs
1. Invest in good primitives, not high-level abstractions
When we first launched Gradio, we offered only one high-level class (gr.Interface), which created a complete web app from a single Python function. We quickly realized that developers wanted to create other kinds of apps (e.g. multi-step workflows, chatbots, streaming applications), but as we started listing out the apps users wanted to build, we realized what we needed to do:
Read the rest here: https://x.com/abidlabs/status/1907886
5 years ago, we launched Gradio as a simple Python library to let researchers at Stanford easily demo computer vision models with a web interface.
Today, Gradio is used by >1 million developers each month to build and share AI web apps. This includes some of the most popular open-source projects of all time, like Automatic1111, Fooocus, Oobabooga’s Text WebUI, Dall-E Mini, and LLaMA-Factory.
How did we get here? How did Gradio keep growing in the very crowded field of open-source Python libraries? I get this question a lot from folks who are building their own open-source libraries. This post distills some of the lessons that I have learned over the past few years:
1. Invest in good primitives, not high-level abstractions
2. Embed virality directly into your library
3. Focus on a (growing) niche
4. Your only roadmap should be rapid iteration
5. Maximize ways users can consume your library's outputs
1. Invest in good primitives, not high-level abstractions
When we first launched Gradio, we offered only one high-level class (gr.Interface), which created a complete web app from a single Python function. We quickly realized that developers wanted to create other kinds of apps (e.g. multi-step workflows, chatbots, streaming applications), but as we started listing out the apps users wanted to build, we realized what we needed to do:
Read the rest here: https://x.com/abidlabs/status/1907886
reactedto fdaudens's post with 🚀 about 1 year ago
Post
2397
See that purple banner on the Llama 4 models? It's Xet storage, and this is actually huge for anyone building with AI models. Let's geek out a little bit 🤓
Current problem: AI models are massive files using Git LFS. But with models getting bigger and downloads exploding, we needed something better.
Xet lets you version large files like code, with compression and deduplication, all Git-compatible. That means less bandwidth, faster sharing, and smoother collaboration.
Real numbers: ~25% deduplication on Llama 4 models, hitting ~40% for finetunes.
Scale matters here - the Hub served 2B model downloads in 30 days, Llama models alone at 60M. The upcoming Llama 4 Behemoth has 2T parameters! Xet's chunk-based system was built exactly for this.
This is the kind of engineering that makes the next wave of large models actually usable. Kudos to the team! 🧨
Check out the models collection: meta-llama/llama-4-67f0c30d9fe03840bc9d0164
Current problem: AI models are massive files using Git LFS. But with models getting bigger and downloads exploding, we needed something better.
Xet lets you version large files like code, with compression and deduplication, all Git-compatible. That means less bandwidth, faster sharing, and smoother collaboration.
Real numbers: ~25% deduplication on Llama 4 models, hitting ~40% for finetunes.
Scale matters here - the Hub served 2B model downloads in 30 days, Llama models alone at 60M. The upcoming Llama 4 Behemoth has 2T parameters! Xet's chunk-based system was built exactly for this.
This is the kind of engineering that makes the next wave of large models actually usable. Kudos to the team! 🧨
Check out the models collection: meta-llama/llama-4-67f0c30d9fe03840bc9d0164