2.24k
The Ultra-Scale Playbook
🌌
The ultimate guide to training LLM on large GPU Clusters
Yan Lu
Jason-Lu
AI & ML interests
sustainable on-device AI & edge-assisted AISys
Recent Activity
liked
a Space
15 days ago
nanotron/ultrascale-playbook
liked
a model
about 2 months ago
openbmb/MiniCPM-o-2_6
upvoted
a
collection
3 months ago
Cosmos Tokenizer
Organizations
Jason-Lu's activity
liked
a
Space
15 days ago
liked
a
model
about 2 months ago
upvoted
a
collection
3 months ago
upvoted
a
paper
7 months ago
liked
2
models
7 months ago
upvoted
a
paper
8 months ago
liked
a
dataset
8 months ago
liked
a
model
8 months ago
upvoted
a
collection
9 months ago
liked
a
model
9 months ago
liked
a
model
10 months ago
reacted to
naskio's
post with 👍
10 months ago
Post
1429
🚀 Meet MergeUI - an All-in-one UI for Exploring Merged LLMs on Hugging Face 🤗!
Model merging is a cool new technique for creating powerful language models for cheap (no GPU required). But it raises questions like:
- Which models should we merge?
- What merge strategies work best?
- How do different base models affect performance?
With MergeUI, you can easily:
- Visualise the family tree and lineage of any merged model.
- Explore benchmark performance of family trees from the Open LLM Leaderboard.
- Analyse the different merge strategies used.
- Check license information for merged models and their ancestors.
All this helps you explore and understand merged models, uncover valuable insights, and make better decisions for your projects.
Ready to dive in? Check out these links:
- 🧬 Try MergeUI - https://naskio-mergeui.hf.space
- 👨💻 Source Code - https://github.com/naskio/mergeui
Love this project? boost it on GitHub and share it with your network.
#merge #mergekit #leaderboard
naskio/mergeui
Model merging is a cool new technique for creating powerful language models for cheap (no GPU required). But it raises questions like:
- Which models should we merge?
- What merge strategies work best?
- How do different base models affect performance?
With MergeUI, you can easily:
- Visualise the family tree and lineage of any merged model.
- Explore benchmark performance of family trees from the Open LLM Leaderboard.
- Analyse the different merge strategies used.
- Check license information for merged models and their ancestors.
All this helps you explore and understand merged models, uncover valuable insights, and make better decisions for your projects.
Ready to dive in? Check out these links:
- 🧬 Try MergeUI - https://naskio-mergeui.hf.space
- 👨💻 Source Code - https://github.com/naskio/mergeui
Love this project? boost it on GitHub and share it with your network.
#merge #mergekit #leaderboard
naskio/mergeui
reacted to
ayush-thakur02's
post with 🔥🤗
11 months ago
Post
2646
Super RAGs in Mistral 8x7B-v1 -
The recent paper on arXiv introduces Super Retrieval-Augmented Generation (Super RAGs), a groundbreaking approach to improve Large Language Models (LLMs) by integrating external knowledge sources. This integration into the Mistral 8x7B v1 LLM has shown notable improvements in accuracy, speed, and user satisfaction.
What are your thoughts on the potential of Super RAGs to transform the future of AI and LLMs?
Introducing Super RAGs in Mistral 8x7B-v1 (2404.08940)
The recent paper on arXiv introduces Super Retrieval-Augmented Generation (Super RAGs), a groundbreaking approach to improve Large Language Models (LLMs) by integrating external knowledge sources. This integration into the Mistral 8x7B v1 LLM has shown notable improvements in accuracy, speed, and user satisfaction.
What are your thoughts on the potential of Super RAGs to transform the future of AI and LLMs?
Introducing Super RAGs in Mistral 8x7B-v1 (2404.08940)
liked
2
models
11 months ago
liked
a
Space
11 months ago
liked
a
model
12 months ago
upvoted
a
collection
about 1 year ago