Come build a knowledge assistant! Our next hackathon is all about Coral. Learn how it was made with Chat and RAG, build new applications, and win cool prizes. Thanks to our hackathon partners @langchain @weaviate_io and @lablabai
. Apply now:
CODE
-
Hackathon Knowledge Assistant: Build with Coral, Chat and RAG
By
–
-
Tokenizer Consistency in RAG Applications and Model Deployment
By
–
If you are using a model from someone else or creating an RAG-based application, be sure to use the same tokenizer (the one most appropriate to your task) for both building your dataset/training and querying (using) the model.
-
Tokenizers Impact on Model Language Comprehension
By
–
Different tokenizers, which is the step where you transform words into understandable numbers for the model, will influence the model's sentence comprehension, too!
-
Monitoring OpenAI API Latency via GitHub Actions
By
–
There was no latency monitoring on the @OpenAI API (which is quite unstable btw) so I made a small automated GitHub repo on GitHub Actions that calls the different ChatCompletion models of OpenAI and logs the response time every hour.
-
Computational Sub-area Emerges Within Prompt Engineering
By
–
cs will be the computational sub area of the prompt engineering department
-
Replicate Improves Training Detail Page with Enhanced Features
By
–
Changelog https://
replicate.com/changelog/2023
-10-17-improved-training-detail-page
… -
XMem and ProPainter: Advanced Video Masking and Inpainting Combined
By
–
XMem plus ProPainter: Combines XMem video masking with ProPainter video inpainting https://
replicate.com/jd7h/xmem-prop
ainter-inpainting
… -
SDXL Canny ControlNet Now Supports LoRA Integration
By
–
SDXL Canny controlnet with LoRA support: Use your Replicate trained loras with Canny controlnet
-
Distributed Systems in 9p Bootcamp Initiative
By
–
yes, but it's still kicking around. i'm using a distributed system as part of the http://
9p.sdf.org bootcamp -
ALiBi Models Performance Extension Without Fine-Tuning
By
–
Unlike existing techniques – this method requires no additional fine tuning. By setting a few parameters in your HuggingFace config.json, you can instantly extend the performance of ALiBi models such as BTLM-3B-8K by ~2x: https://
huggingface.co/cerebras/btlm-
3b-8k-base#during-inference-without-fine-tuning
…