Mistral 7B - The Llama Killer Finetune and Inference for Custom Usecase
7.8 هزار بار بازدید -
9 ماه پیش
-
🚀 Mistral-7B-Instruct: A High-Performance MarvelIn
🚀 Mistral-7B-Instruct: A High-Performance Marvel
In this video, we delve into the fine-tuning of Mistral-7B-Instruct, the latest SOTA model from the innovative French startup, Mistral AI. And yes, it's all happening within Google Colab's free version!
🏆 Outshining the Competition
Discover how Mistral-7B-Instruct surpasses all 7B models, including Llama2 7B, 13B, and even Llama 34B models.
🗣️ Crafting Dialogue Summarization Excellence
Witness the magic as we fine-tune Mistral-7B-Instruct for a custom use-case, dialogue summarization. Join us in exploring and harnessing the unmatched power of Mistral-7B for top-tier performance! 🌐🤖🔥
Links:
Github Repo: https://github.com/Vasanthengineer494...
Technical Blog: https://huggingface.co/TheBloke/Mistr...
Model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
In this video, we delve into the fine-tuning of Mistral-7B-Instruct, the latest SOTA model from the innovative French startup, Mistral AI. And yes, it's all happening within Google Colab's free version!
🏆 Outshining the Competition
Discover how Mistral-7B-Instruct surpasses all 7B models, including Llama2 7B, 13B, and even Llama 34B models.
🗣️ Crafting Dialogue Summarization Excellence
Witness the magic as we fine-tune Mistral-7B-Instruct for a custom use-case, dialogue summarization. Join us in exploring and harnessing the unmatched power of Mistral-7B for top-tier performance! 🌐🤖🔥
Links:
Github Repo: https://github.com/Vasanthengineer494...
Technical Blog: https://huggingface.co/TheBloke/Mistr...
Model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
9 ماه پیش
در تاریخ 1402/07/08 منتشر شده
است.
7,896
بـار بازدید شده