Sourab Mangrulkar

smangrul's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a Space 12 days ago

Running

10

📚

PEFT Docs QA Chatbot

liked a model 2 months ago

BlinkDL/rwkv-4-pile-169m

Text Generation • Updated Mar 13, 2023 • 10

liked 2 models 3 months ago

meta-llama/Llama-3.1-8B-Instruct

Text Generation • Updated Sep 25 • 6.59M • • 3.11k

microsoft/Phi-3.5-mini-instruct

Text Generation • Updated Sep 18 • 591k • • 654

liked a model 4 months ago

microsoft/Phi-3-mini-128k-instruct

Text Generation • Updated Aug 20 • 1.03M • 1.61k

liked a model 5 months ago

microsoft/Phi-3-mini-4k-instruct

Text Generation • Updated Sep 20 • 1.51M • • 1.08k

upvoted a collection 5 months ago

Phi-3

Collection

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 26 items • Updated 11 days ago • 498

liked a dataset 7 months ago

internlm/Agent-FLAN

Preview • Updated Mar 20 • 106 • 65

liked a Space 7 months ago

Running

87

🐠

Nexus Function Calling Leaderboard

liked a model 7 months ago

gorilla-llm/gorilla-openfunctions-v2

Text Generation • Updated Apr 18 • 11.2k • 213

liked a dataset 7 months ago

smangrul/hug_stack

Viewer • Updated Feb 2 • 6.58k • 117 • 3

updated a model 7 months ago

smangrul/peft-lora-whisper-largev2-cv11-mr-t4-colab

Updated Apr 23 • 7 • 1

liked a model 7 months ago

smangrul/falcon-180B-chat-asst-ds-lora

Updated Oct 2, 2023 • 2 • 1

posted an update 7 months ago

view post

Post

3199

Reply

Unlocking the Power of locally running Llama-3 8B Model Agents with Chat-UI! 🔥🚀✨

I'm thrilled to share my hackathon-style side project:
1. Finetuning Llama-8B for function calling using PEFT QLoRA as the instruct Llama-3 model doesn't support this. The colab notebook for it is here: https://lnkd.in/ggJMzqh2. 🛠️
2. Finetuned model along with the 4-bit quants here: https://lnkd.in/gNpFKY6V ✨
3. Clone Hugging Face https://lnkd.in/gKBKuUBQ and make it compatible for function calling by building upon the PR https://lnkd.in/gnqFuAd4 for my model and local inferencing usecase using Ollama. This was a steep learning curve wherein I stayed awake the whole night to get it working. 💪🏽
4. Above, I used SerpAPI for web browsing and Mongo DB Atlas free tier for persistence of conversations and assistant configs. 🔎
5. More work is required to switch between using tools and responding directly wherein I see the model breaks. 🧐

How cool is this wherein we are approaching experience akin to ChatGPT while using local hosted agent model running on your laptop! 💻

• 
• 1 reply

·

🤯

9

9

🔥

8

8

+

updated a model 7 months ago

smangrul/llama-3-8B-instruct-function-calling

Updated Apr 21 • 20 • 28

liked a model 7 months ago

smangrul/llama-3-8B-instruct-function-calling

Updated Apr 21 • 20 • 28

upvoted an article 7 months ago

view article

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 278

liked 2 models 7 months ago

unsloth/llama-3-8b-Instruct-bnb-4bit

Text Generation • Updated 3 days ago • 96.2k • 130

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • Updated Sep 27 • 2.66M • • 3.64k

liked a dataset 7 months ago

glaiveai/glaive-code-assistant-v3

Viewer • Updated May 20 • 950k • 384 • 44