zerofata/Q3.5-BlueStar-v2-27B
27B • Updated • 61 • 11
Paweł Kozon
PKPL
AI & ML interests
only Ai for fun
Recent Activity
liked a model about 21 hours ago
zerofata/Q3.5-BlueStar-v2-27B liked a model 4 days ago
mistralai/Mistral-Small-4-119B-2603 liked a model 10 months ago
Sao10K/Lmao_life_updatesOrganizations
None yet
liked a
model about 21 hours ago
liked a
model 4 days ago
liked a
model 10 months ago
liked 4
models over 1 year ago
reactedto anakin87's post with 👍 over 1 year ago
Post
1777
🕵🏻 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).
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).
liked 2
models over 1 year ago
liked 6
models almost 2 years ago
jeiku/Chaos_RP_l3_8B
Text Generation • 8B • Updated • 9 • • 20
ChaoticNeutrals/RPMix-4x7B-MoE
Text Generation • 24B • Updated • 119 • 9
ParasiticRogue/Merged-RP-Stew-V2-34B
Text Generation • 34B • Updated • 12 • 58
Sao10K/Fimbulvetr-11B-v2
Text Generation • 11B • Updated • 473 • • 190
KatyTheCutie/LemonadeRP-4.5.3
Text Generation • 7B • Updated • 211 • 60
brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity
Text Generation • 34B • Updated • 771 • 12
liked 4
models about 2 years ago
