How to chat with your PDFs using local Large Language Models [Ollama RAG] Covers loading PDFs with Unstructured, splitting that text data with RecursiveCharacterTextSplitter, creating embeddings with Ollama https://
youtube.com/watch?v=ztBJqz
BU5kc&t=1s
…
OPEN SOURCE
-
Chat with PDFs Using Local LLMs and Ollama RAG
By
–
-
CrowdLab: Python Library for Consensus Labels and Quality Scoring
By
–
This Python library works like magic! With a single line of code & the two matrices you see in the image below, I can find: – a consensus label
– quality score for individual & consensus labels
– overall quality score for each annotator Introducing CrowdLab! A weighted -
Open LLM Leaderboard Results Excluding GSM8K
By
–
all on open llm lb except gsm8k. dont see the screenshot? lol
-
Passport.js Authentication Library Impact and Use Cases
By
–
“What has passportjs ever done for you”
-
Fast LLaMA 3 Fine-tuning with ORPO on 8xH100 GPUs
By
–
all info available in the model page: https://
huggingface.co/abhishek/autot
rain-llama3-orpo
… 🙂 finetuning took ~30 mins on 8xH100 -
AutoTrain Fine-tuned Llama3 Outperforms Base Instruct Model
By
–
AutoTrain finetuned llama3 beats the base instruct model on all but one benchmark on the open llm leaderboard This model was finetuned using ORPO and is also publicly available. No code was written and all the setup took less than 10mins. `pip install autotrain-advanced`
-
Open-source AI models: commitment and strategic choices
By
–
I have some opinions on this matter. I don’t think everything needs to be open-source, but for models that companies decide that it is strategically better for them to release, they might as well go all the way.
-
Apache-2 Licensing vs Restrictive Community Licenses Debate
By
–
This is controversial, but I’d rather see companies release Apache-2 licensed models, but keep certain models proprietary, than release everything under some non-open-source restrictive “community” license, which has the adverse effect of encouraging and normalizing restrictions.
-
Groq and Llama3: 24 Hours of Development Updates
By
–
24 hours for Groq and #Llama3. Read more about today's developments at https://
groq.link/llama3blog. -
Need Apache-2.0 Licenses for Open-Source AI Acceleration
By
–
Although I must say that we need more Apache-2.0 style licenses, and less of these “non-commercial, research only” restrictive ‘community’ licenses for model releases to really accelerate open-source AI adoption.