Teaching GPT-OSS-20B to Reason via Finetuning using RunPods ! 😲 скачать в хорошем качестве

Teaching GPT-OSS-20B to Reason via Finetuning using RunPods ! 😲

Try out RunPods GPU: https://get.runpod.io/pe48 In this video, we walk through how to fine-tune OpenAI’s open-weight reasoning model, gpt-oss-20b, so it can think and reason in multiple languages — not just English. 🌍 We’ll use Hugging Face Transformers, TRL, and LoRA to make the model generate its chain-of-thought in languages like Spanish, French, German, and more — all while keeping VRAM usage low. CHANNEL LINKS: 🕵️‍♀️ Join my Patreon for keeping up with the updates:   / promptengineer975   ☕ Buy me a coffee: https://ko-fi.com/promptengineer 📞 Get on a Call with me at Calendly: https://calendly.com/prompt-engineer4... 💀 GitHub Profile: https://github.com/PromptEngineer48 🔖 Twitter Profile:   / prompt48   Hastags: #finetuning, #openai_funetuning, #get-oss-finetuning, #trl, #peft, #lora, #transformers, #huggingface, #multilingual Link of the codes: https://github.com/PromptEngineer48/g... TimeStamp: 0:00 Intro 1:36 Start Runpods 2:38 Update the Pod 3:35 Installations 4:14 Huggingface 4:54 Dataset Preparation 6:49 Loading the Dataset 9:23 Load the Model 10:33 Running the Model 10:59 Peft Model 12:49 Set Hyperparameters 13:35 Load the Trainer 14:47 Train the Model 15:20 Save the Model and Push to Hub 16:31 Use the Trained Model 18:49 Summary