s3nh
s3nh
AI & ML interests
Quantization, LLMs, Deep Learning for good. Follow me if you like my work. Patreon.com/s3nh
Recent Activity
reacted
to
as-cle-bert's
post
with โค๏ธ
8 days ago
I just released a fully automated evaluation framework for your RAG applications!๐
GitHub ๐ https://github.com/AstraBert/diRAGnosis
PyPi ๐ https://pypi.org/project/diragnosis/
It's called ๐๐ข๐๐๐๐ง๐จ๐ฌ๐ข๐ฌ and is a lightweight framework that helps you ๐ฑ๐ถ๐ฎ๐ด๐ป๐ผ๐๐ฒ ๐๐ต๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ผ๐ณ ๐๐๐ ๐ ๐ฎ๐ป๐ฑ ๐ฟ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ถ๐ป ๐ฅ๐๐ ๐ฎ๐ฝ๐ฝ๐น๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป๐.
You can launch it as an application locally (it's Docker-ready!๐) or, if you want more flexibility, you can integrate it in your code as a python package๐ฆ
The workflow is simple:
๐ง You choose your favorite LLM provider and model (supported, for now, are Mistral AI, Groq, Anthropic, OpenAI and Cohere)
๐ง You pick the embedding models provider and the embedding model you prefer (supported, for now, are Mistral AI, Hugging Face, Cohere and OpenAI)
๐ You prepare and provide your documents
โ๏ธ Documents are ingested into a Qdrant vector database and transformed into a synthetic question dataset with the help of LlamaIndex
๐ The LLM is evaluated for the faithfulness and relevancy of its retrieval-augmented answer to the questions
๐ The embedding model is evaluated for hit rate and mean reciprocal ranking (MRR) of the retrieved documents
And the cool thing is that all of this is ๐ถ๐ป๐๐๐ถ๐๐ถ๐๐ฒ ๐ฎ๐ป๐ฑ ๐ฐ๐ผ๐บ๐ฝ๐น๐ฒ๐๐ฒ๐น๐ ๐ฎ๐๐๐ผ๐บ๐ฎ๐๐ฒ๐ฑ: you plug it in, and it works!๐โก
Even cooler? This is all built on top of LlamaIndex and its integrations: no need for tons of dependencies or fancy workarounds๐ฆ
And if you're a UI lover, Gradio and FastAPI are there to provide you a seamless backend-to-frontend experience๐ถ๏ธ
So now it's your turn: you can either get diRAGnosis from GitHub ๐ https://github.com/AstraBert/diRAGnosis
or just run a quick and painless:
```bash
uv pip install diragnosis
```
To get the package installed (lightning-fast) in your environment๐โโ๏ธ
Have fun and feel free to leave feedback and feature/integrations requests on GitHub issuesโจ
reacted
to
as-cle-bert's
post
with ๐
8 days ago
I just released a fully automated evaluation framework for your RAG applications!๐
GitHub ๐ https://github.com/AstraBert/diRAGnosis
PyPi ๐ https://pypi.org/project/diragnosis/
It's called ๐๐ข๐๐๐๐ง๐จ๐ฌ๐ข๐ฌ and is a lightweight framework that helps you ๐ฑ๐ถ๐ฎ๐ด๐ป๐ผ๐๐ฒ ๐๐ต๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ผ๐ณ ๐๐๐ ๐ ๐ฎ๐ป๐ฑ ๐ฟ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ถ๐ป ๐ฅ๐๐ ๐ฎ๐ฝ๐ฝ๐น๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป๐.
You can launch it as an application locally (it's Docker-ready!๐) or, if you want more flexibility, you can integrate it in your code as a python package๐ฆ
The workflow is simple:
๐ง You choose your favorite LLM provider and model (supported, for now, are Mistral AI, Groq, Anthropic, OpenAI and Cohere)
๐ง You pick the embedding models provider and the embedding model you prefer (supported, for now, are Mistral AI, Hugging Face, Cohere and OpenAI)
๐ You prepare and provide your documents
โ๏ธ Documents are ingested into a Qdrant vector database and transformed into a synthetic question dataset with the help of LlamaIndex
๐ The LLM is evaluated for the faithfulness and relevancy of its retrieval-augmented answer to the questions
๐ The embedding model is evaluated for hit rate and mean reciprocal ranking (MRR) of the retrieved documents
And the cool thing is that all of this is ๐ถ๐ป๐๐๐ถ๐๐ถ๐๐ฒ ๐ฎ๐ป๐ฑ ๐ฐ๐ผ๐บ๐ฝ๐น๐ฒ๐๐ฒ๐น๐ ๐ฎ๐๐๐ผ๐บ๐ฎ๐๐ฒ๐ฑ: you plug it in, and it works!๐โก
Even cooler? This is all built on top of LlamaIndex and its integrations: no need for tons of dependencies or fancy workarounds๐ฆ
And if you're a UI lover, Gradio and FastAPI are there to provide you a seamless backend-to-frontend experience๐ถ๏ธ
So now it's your turn: you can either get diRAGnosis from GitHub ๐ https://github.com/AstraBert/diRAGnosis
or just run a quick and painless:
```bash
uv pip install diragnosis
```
To get the package installed (lightning-fast) in your environment๐โโ๏ธ
Have fun and feel free to leave feedback and feature/integrations requests on GitHub issuesโจ
reacted
to
MonsterMMORPG's
post
with ๐ฅ
24 days ago
Wan 2.1 Ultra Advanced Gradio APP for - Works as low as 4GB VRAM - 1-Click Installers for Windows, RunPod, Massed Compute - Batch Processing - T2V - I2V - V2V
Installer and APP : https://www.patreon.com/posts/123105403
Download from here : https://www.patreon.com/posts/123105403
I have been working 14 hours today to make this APP before sleeping for you guys :)
We have all the features of Wan 2.1 model
Text to Video 1.3B (as low as 3.5 GB VRAM) - Really fast - 480x832px or 832x480px
Video to Video 1.3B (as low as 3.5 GB VRAM) - Really fast - 480x832px or 832x480px
Text to Video 14B (as low as 17 GB VRAM) - still may work at below VRAM but slower - 720x1280px or 1280x720px
Image to Video 14B (as low as 17 GB VRAM) - still may work at below VRAM but slower - 720x1280px or 1280x720px
When you analyze the above and below images
First video is animated from the input image with following prompt
A hooded wraith stands motionless in a torrential downpour, lightning cracking across the stormy sky behind it. Its face is an impenetrable void of darkness beneath the tattered hood. Rain cascades down its ragged, flowing cloak, which appears to disintegrate into wisps of shadow at the edges. The mysterious figure holds an enormous sword of pure energy, crackling with electric blue lightning that pulses and flows through the blade like liquid electricity. The weapon drags slightly on the wet ground, sending ripples of power across the puddles forming at the figure's feet. Three glowing blue gems embedded in its chest pulse in rhythm with the storm's lightning strikes, each flash illuminating the decaying, ancient fabric of its attire. The rain intensifies around the figure, droplets seemingly slowing as they near the dark entity, while forks of lightning repeatedly illuminate its imposing silhouette. The atmosphere grows heavier with each passing moment as the wraith slowly raises its crackling blade, the blue energy intensifying and casting eerie shadows
Organizations
s3nh's activity
Adding `safetensors` variant of this model
#1 opened about 2 months ago
by
SFconvertbot
Gh organization
8
#3 opened 3 months ago
by
s3nh
Optimizers
#2 opened 3 months ago
by
s3nh
Datasets
3
#1 opened 3 months ago
by
s3nh
Create model card with metadata
#1 opened about 1 year ago
by
osanseviero
Create model card with metadata
#1 opened about 1 year ago
by
osanseviero
Adding Evaluation Results
#2 opened about 1 year ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened about 1 year ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened about 1 year ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened about 1 year ago
by
leaderboard-pr-bot
RuntimeError: CUDA must not be initialized in the main process on Spaces with Stateless GPU environment.
2
#6 opened about 1 year ago
by
mrfakename
error loading model: create_tensor: tensor 'output.weight' not found ?
6
#1 opened about 1 year ago
by
wukongai
Hello bro
12
#1 opened about 1 year ago
by
Abhaykoul
Librarian Bot: Add base_model metadata to model
#2 opened about 1 year ago
by
librarian-bot
Librarian Bot: Add merge tag to model
#1 opened about 1 year ago
by
librarian-bot
Problem with Quants
5
#2 opened about 1 year ago
by
Clevyby
Thanks :)
1
#1 opened about 1 year ago
by
BlueNipples
not able to post after exceed message length once
1
#19 opened about 1 year ago
by
s3nh
Deleted GGUF?
6
#1 opened about 1 year ago
by
EloyOn