Serve a Custom LLM Trained with RLHF in - FREE COLAB 📓
This is the second part to the video, where I show you how to inference the model trained using reinforment learning with human feedback. In the first video we had fine-tune LLaMA 2 (and other LLMs like mistral 7b) for your specific use case. This allows your GPT model to perform much better for your business or personal use case. Given gpt like model mistral detailed information that it doesn't already have, make it respond in a specific tone/personality, and much more.
In this tutorial, we will host our model trained using reinforcement learning with human feed back(rlhf) l, where in first video we had train our model to only generate positive response. This technique can be further finetuned to create a chatbot which will be free from violent speech and any user can use it.
In this video, I will show you how to build your own open-source CHATGPT . Fine-tuning the mistal, gpt,llama like model can provide several benefits, including improved performance, cost savings, and customization.
Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)
First part: • Fine Tune GPT In FIVE MINUTES with RLHF! -...
Chapters:
0:00 Intro
0.28 Example of why we dont use feedback
1.48 Save model trained using rlhf
2:28 Installition of gradio
3:08 Testing if model gives accurate answer
✍️Learn and write the code along with me.
🙏The hand promises that if you subscribe to the channel and like this video, it will release more tutorial videos.
👐I look forward to seeing you in future videos
LINK :
Dataset: https://www.kaggle.com/datasets/laksh...
Policy Model: https://huggingface.co/lvwerra/gpt2-imdb
Reward Model: https://huggingface.co/lvwerra/distil...
Notebook: https://github.com/ashishjamarkattel/...
#gpt #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #langchain #largelanguagemodels #largelanguagemodel #bestaiagent #chatgpt #embedding #llama2 #openaiembeddings #wordembeddings #largelanguagemodels #rlhf #whisperingai #finetuning#llama2 #finetuning #autotrain #huggingface