Paweł Kozon

PKPL

AI & ML interests

only Ai for fun

Recent Activity

liked a model 15 days ago

AuraIndustries/Aura-8B

liked a model 19 days ago

Sao10K/I_am_alive_yay

liked a model about 2 months ago

VongolaChouko/Starcannon-Unleashed-12B-v1.0

View all activity

Organizations

None yet

PKPL's activity

liked a model 15 days ago

AuraIndustries/Aura-8B

Updated 15 days ago • 72 • 7

liked a model 19 days ago

Sao10K/I_am_alive_yay

Updated 27 days ago • 62

liked 2 models about 2 months ago

VongolaChouko/Starcannon-Unleashed-12B-v1.0

Text Generation • Updated Nov 2 • 361 • 37

Nohobby/MS-Schisandra-22B-v0.1

Text Generation • Updated Nov 3 • 17 • 5

reacted to anakin87's post with 👍 3 months ago

Post

1735

🕵🏻 𝐀𝐠𝐞𝐧𝐭𝐢𝐜 𝐑𝐀𝐆 𝐰𝐢𝐭𝐡 🦙 𝐋𝐥𝐚𝐦𝐚 3.2

I was excited to explore Llama 3.2, but as a simple 🇪🇺 EU guy, I don't have access to Meta's multimodal models 😿

🤔 So I thought: why not challenge the small 3B text model with Agentic RAG?

🎯 The plan:
- Build a system that tries to answer questions using a knowledge base.
- If the documents don't contain the answer, use Web search for additional context.

Check out my experimental notebook here: 📓 https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/llama32_agentic_rag.ipynb

My stack:
🏗️ haystack (https://haystack.deepset.ai/): open-source LLM orchestration framework
🦙 meta-llama/Llama-3.2-3B-Instruct
🦆🌐 free DuckDuckGo API, integrated with Haystack

✨ 𝘛𝘩𝘦 𝘳𝘦𝘴𝘶𝘭𝘵𝘴? 𝘌𝘯𝘤𝘰𝘶𝘳𝘢𝘨𝘪𝘯𝘨 - 𝘢 𝘧𝘦𝘸 𝘮𝘰𝘯𝘵𝘩𝘴 𝘢𝘨𝘰, 𝘵𝘩𝘪𝘴 𝘭𝘦𝘷𝘦𝘭 𝘰𝘧 𝘱𝘦𝘳𝘧𝘰𝘳𝘮𝘢𝘯𝘤𝘦 𝘧𝘳𝘰𝘮 𝘢 𝘴𝘮𝘢𝘭𝘭 𝘮𝘰𝘥𝘦𝘭 𝘸𝘰𝘶𝘭𝘥'𝘷𝘦 𝘣𝘦𝘦𝘯 𝘶𝘯𝘵𝘩𝘪𝘯𝘬𝘢𝘣𝘭𝘦!
This probably reflects the impressive IFEval score of the model (comparable to Llama 3.1 8B).