perplexity-ai/r1-1776
Updated
•
7.75k
•
1.53k
Nick Brooks
nickandbro
AI & ML interests
None yet
Recent Activity
liked
a model
4 days ago
perplexity-ai/r1-1776
new activity
4 days ago
perplexity-ai/r1-1776:Uncensored Dataset 2 open source
reacted
to
singhsidhukuldeep's
post
with 🚀
about 1 month ago
Breaking News: LinkedIn's Content Search Engine Gets a Powerful Semantic Upgrade!
Excited to share insights about LinkedIn's innovative approach to content search, recently detailed in a groundbreaking paper by their Mountain View team. This advancement represents a significant shift from traditional keyword-based search to semantic understanding.
>> Technical Architecture
The new search engine employs a sophisticated two-layer architecture:
Retrieval Layer
- Token Based Retriever (TBR) for exact keyword matching
- Embedding Based Retriever (EBR) using a two-tower model with multilingual-e5 embeddings
- Pre-computed post embeddings stored in a dedicated embedding store for efficient retrieval
Multi-Stage Ranking
- L1 Stage: Initial filtering using a lightweight model
- L2 Stage: Advanced ranking with complex features including:
- Query-post semantic matching
- Author reputation analysis
- User engagement metrics
- Content freshness evaluation
>> Performance Improvements
The system has achieved remarkable results:
- 10%+ improvement in both on-topic rate and long-dwell metrics
- Enhanced ability to handle complex natural language queries
- Significant boost in sitewide engagement
This advancement enables LinkedIn to better serve complex queries like "how to ask for a raise?" while maintaining high performance at scale. The system intelligently balances between exact keyword matching and semantic understanding, ensuring optimal results for both navigational and conceptual searches.
What impresses me most is how the team solved the scale challenge - processing billions of posts efficiently using pre-computed embeddings and approximate nearest neighbor search. This is enterprise-scale AI at its finest.
Organizations
nickandbro's activity
liked
a
model
4 days ago
Uncensored Dataset 2 open source
3
#31 opened 4 days ago
by
ledjo
reacted to
singhsidhukuldeep's
post with 🚀
about 1 month ago
Post
1123
Breaking News: LinkedIn's Content Search Engine Gets a Powerful Semantic Upgrade!
Excited to share insights about LinkedIn's innovative approach to content search, recently detailed in a groundbreaking paper by their Mountain View team. This advancement represents a significant shift from traditional keyword-based search to semantic understanding.
>> Technical Architecture
The new search engine employs a sophisticated two-layer architecture:
Retrieval Layer
- Token Based Retriever (TBR) for exact keyword matching
- Embedding Based Retriever (EBR) using a two-tower model with multilingual-e5 embeddings
- Pre-computed post embeddings stored in a dedicated embedding store for efficient retrieval
Multi-Stage Ranking
- L1 Stage: Initial filtering using a lightweight model
- L2 Stage: Advanced ranking with complex features including:
- Query-post semantic matching
- Author reputation analysis
- User engagement metrics
- Content freshness evaluation
>> Performance Improvements
The system has achieved remarkable results:
- 10%+ improvement in both on-topic rate and long-dwell metrics
- Enhanced ability to handle complex natural language queries
- Significant boost in sitewide engagement
This advancement enables LinkedIn to better serve complex queries like "how to ask for a raise?" while maintaining high performance at scale. The system intelligently balances between exact keyword matching and semantic understanding, ensuring optimal results for both navigational and conceptual searches.
What impresses me most is how the team solved the scale challenge - processing billions of posts efficiently using pre-computed embeddings and approximate nearest neighbor search. This is enterprise-scale AI at its finest.
Excited to share insights about LinkedIn's innovative approach to content search, recently detailed in a groundbreaking paper by their Mountain View team. This advancement represents a significant shift from traditional keyword-based search to semantic understanding.
>> Technical Architecture
The new search engine employs a sophisticated two-layer architecture:
Retrieval Layer
- Token Based Retriever (TBR) for exact keyword matching
- Embedding Based Retriever (EBR) using a two-tower model with multilingual-e5 embeddings
- Pre-computed post embeddings stored in a dedicated embedding store for efficient retrieval
Multi-Stage Ranking
- L1 Stage: Initial filtering using a lightweight model
- L2 Stage: Advanced ranking with complex features including:
- Query-post semantic matching
- Author reputation analysis
- User engagement metrics
- Content freshness evaluation
>> Performance Improvements
The system has achieved remarkable results:
- 10%+ improvement in both on-topic rate and long-dwell metrics
- Enhanced ability to handle complex natural language queries
- Significant boost in sitewide engagement
This advancement enables LinkedIn to better serve complex queries like "how to ask for a raise?" while maintaining high performance at scale. The system intelligently balances between exact keyword matching and semantic understanding, ensuring optimal results for both navigational and conceptual searches.
What impresses me most is how the team solved the scale challenge - processing billions of posts efficiently using pre-computed embeddings and approximate nearest neighbor search. This is enterprise-scale AI at its finest.
liked
a
model
about 2 months ago
What is an actorder group and what are the advantages of running this in vLLM?
4
#1 opened about 2 months ago
by
nickandbro
Compatible with vLLM?
#4 opened 2 months ago
by
nickandbro
liked
a
model
2 months ago
Will this work with vLLM?
4
#10 opened 3 months ago
by
nickandbro
Can you please add Nemotron 70B static?
3
#1 opened 4 months ago
by
nickandbro
Congrats to the Nvidia team!
#10 opened 4 months ago
by
nickandbro
vLLM compatible?
3
#10 opened 5 months ago
by
nickandbro
reacted to
davidberenstein1957's
post with 👍
4 months ago
Post
2502
Don't use an LLM when you can use a much cheaper model.
The problem is that no one tells you how to actually do it.
Just picking a pre-trained model (e.g., BERT) and throwing it at your problem won't work!
If you want a small model to perform well on your problem, you need to fine-tune it.
And to fine-tune it, you need data.
The good news is that you don't need a lot of data but instead high-quality data for your specific problem.
In the latest livestream, I showed you guys how to get started with Argilla on the Hub! Hope to see you at the next one.
https://www.youtube.com/watch?v=BEe7shiG3rY
The problem is that no one tells you how to actually do it.
Just picking a pre-trained model (e.g., BERT) and throwing it at your problem won't work!
If you want a small model to perform well on your problem, you need to fine-tune it.
And to fine-tune it, you need data.
The good news is that you don't need a lot of data but instead high-quality data for your specific problem.
In the latest livestream, I showed you guys how to get started with Argilla on the Hub! Hope to see you at the next one.
https://www.youtube.com/watch?v=BEe7shiG3rY
liked
a
model
5 months ago
reacted to
zamal's
post with 🤗
5 months ago
Post
1954
🚀 New Model Release: zamal/Molmo-7B-GPTQ-4bit 🚀
Hello lovely community,
zamal/Molmo-7B-GPTQ-4bit model is now available for all! This model has been highly quantized, reducing its size by almost six times. It now occupies significantly less space and vRAM, making it perfect for deployment on resource-constrained devices without compromising performance.
Now we get:
Efficient Performance: Maintains high accuracy while being highly quantized.
Reduced Size: The model size is reduced by nearly six times, optimizing storage and memory usage.
Versatile Application: Ideal for integrating a powerful visual language model into various projects particularly multi rag chains.
Check it out!
Hello lovely community,
zamal/Molmo-7B-GPTQ-4bit model is now available for all! This model has been highly quantized, reducing its size by almost six times. It now occupies significantly less space and vRAM, making it perfect for deployment on resource-constrained devices without compromising performance.
Now we get:
Efficient Performance: Maintains high accuracy while being highly quantized.
Reduced Size: The model size is reduced by nearly six times, optimizing storage and memory usage.
Versatile Application: Ideal for integrating a powerful visual language model into various projects particularly multi rag chains.
Check it out!
- 1 reply
Does this work with vLLM?
#9 opened 5 months ago
by
nickandbro
reacted to
MonsterMMORPG's
post with ❤️
5 months ago
Post
4199
Trained Myself With 256 Images on FLUX — Results Mind Blowing
Detailed Full Workflow
Medium article : https://medium.com/@furkangozukara/ultimate-flux-lora-training-tutorial-windows-and-cloud-deployment-abb72f21cbf8
Windows main tutorial : https://youtu.be/nySGu12Y05k
Cloud tutorial for GPU poor or scaling : https://youtu.be/-uhL2nW7Ddw
Full detailed results and conclusions : https://www.patreon.com/posts/111891669
Full config files and details to train : https://www.patreon.com/posts/110879657
SUPIR Upscaling (default settings are now perfect) : https://youtu.be/OYxVEvDf284
I used my Poco X6 Camera phone and solo taken images
My dataset is far from being ready, thus I have used so many repeating and almost same images, but this was rather experimental
Hopefully I will continue taking more shots and improve dataset and reduce size in future
I trained Clip-L and T5-XXL Text Encoders as well
Since there was too much push from community that my workflow won’t work with expressions, I had to take a break from research and use whatever I have
I used my own researched workflow for training with Kohya GUI and also my own self developed SUPIR app batch upscaling with face upscaling and auto LLaVA captioning improvement
Download images to see them in full size, the last provided grid is 50% downscaled
Workflow
Gather a dataset that has expressions and perspectives that you like after training, this is crucial, whatever you add, it can generate perfect
Follow one of the LoRA training tutorials / guides
After training your LoRA, use your favorite UI to generate images
I prefer SwarmUI and here used prompts (you can add specific expressions to prompts) including face inpainting :
https://gist.github.com/FurkanGozukara/ce72861e52806c5ea4e8b9c7f4409672
After generating images, use SUPIR to upscale 2x with maximum resemblance
Short Conclusions
Using 256 images certainly caused more overfitting than necessary
...
Detailed Full Workflow
Medium article : https://medium.com/@furkangozukara/ultimate-flux-lora-training-tutorial-windows-and-cloud-deployment-abb72f21cbf8
Windows main tutorial : https://youtu.be/nySGu12Y05k
Cloud tutorial for GPU poor or scaling : https://youtu.be/-uhL2nW7Ddw
Full detailed results and conclusions : https://www.patreon.com/posts/111891669
Full config files and details to train : https://www.patreon.com/posts/110879657
SUPIR Upscaling (default settings are now perfect) : https://youtu.be/OYxVEvDf284
I used my Poco X6 Camera phone and solo taken images
My dataset is far from being ready, thus I have used so many repeating and almost same images, but this was rather experimental
Hopefully I will continue taking more shots and improve dataset and reduce size in future
I trained Clip-L and T5-XXL Text Encoders as well
Since there was too much push from community that my workflow won’t work with expressions, I had to take a break from research and use whatever I have
I used my own researched workflow for training with Kohya GUI and also my own self developed SUPIR app batch upscaling with face upscaling and auto LLaVA captioning improvement
Download images to see them in full size, the last provided grid is 50% downscaled
Workflow
Gather a dataset that has expressions and perspectives that you like after training, this is crucial, whatever you add, it can generate perfect
Follow one of the LoRA training tutorials / guides
After training your LoRA, use your favorite UI to generate images
I prefer SwarmUI and here used prompts (you can add specific expressions to prompts) including face inpainting :
https://gist.github.com/FurkanGozukara/ce72861e52806c5ea4e8b9c7f4409672
After generating images, use SUPIR to upscale 2x with maximum resemblance
Short Conclusions
Using 256 images certainly caused more overfitting than necessary
...
Is this compatible with the KV_Cache_dtype being FP8?
2
#1 opened 7 months ago
by
nickandbro
liked
a
model
7 months ago
Where can I find the code?
3
#832 opened 8 months ago
by
nickandbro
reacted to
tomaarsen's
post with 🔥
10 months ago
Post
2408
NuMind has just released 3 new state-of-the-art GLiNER models for Named Entity Recognition/Information Extraction. These GLiNER models allow you to specify any label that you want, and it'll find spans in the text corresponding to your label. It's been shown to work quite well on unusual domains, e.g. celestial entities in my picture.
There are 3 models released:
- numind/NuNER_Zero:
The primary model, SOTA & can detect really long entities.
- numind/NuNER_Zero-span:
Slightly better performance than NuNER Zero, but can't detect entities longer than 12 tokens.
- numind/NuNER_Zero-4k:
Slightly worse than NuNER Zero, but has a context length of 4k tokens.
Some more details about these models in general:
- They are *really* small, orders of magnitude smaller than LLMs, which don't reach this level of performance.
- Because they're small - they're fast: <1s per sentence on free GPUs.
- They have an MIT license: free commercial usage.
Try out the demo here: https://huggingface.co/spaces/numind/NuZero
Or check out all of the models here: numind/nunerzero-zero-shot-ner-662b59803b9b438ff56e49e2
If there's ever a need for me to extract some information from any text: I'll be using these. Great work @Serega6678 !
There are 3 models released:
- numind/NuNER_Zero:
The primary model, SOTA & can detect really long entities.
- numind/NuNER_Zero-span:
Slightly better performance than NuNER Zero, but can't detect entities longer than 12 tokens.
- numind/NuNER_Zero-4k:
Slightly worse than NuNER Zero, but has a context length of 4k tokens.
Some more details about these models in general:
- They are *really* small, orders of magnitude smaller than LLMs, which don't reach this level of performance.
- Because they're small - they're fast: <1s per sentence on free GPUs.
- They have an MIT license: free commercial usage.
Try out the demo here: https://huggingface.co/spaces/numind/NuZero
Or check out all of the models here: numind/nunerzero-zero-shot-ner-662b59803b9b438ff56e49e2
If there's ever a need for me to extract some information from any text: I'll be using these. Great work @Serega6678 !
- 3 replies