LoRA ile eğit

RLHF ile ince ayara başlamak istedin ama sürekli bellek yetersizliği hataları aldın. Modeli 8-bit duyarlılıkla yüklemeye geçmene rağmen hata devam etti. Bunu çözmek için bir sonraki adıma geçip daha verimli ince ayar için LoRA uygulamaya karar verdin.

Aşağıdakiler önceden içe aktarıldı:

8-bit duyarlılıkla yüklenmiş model: pretrained_model_8bit
peft içinden LoraConfig ve get_peft_model
trl içinden AutoModelForCausalLMWithValueHead

Bu egzersiz

İnsan Geri Bildiriminden Pekiştirmeli Öğrenme (RLHF)

kursunun bir parçasıdır

Kursu Görüntüle

Egzersiz talimatları

LoRA dropout değerini 0.1 yap ve bias türünü yalnızca lora olacak şekilde ayarla.
LoRA yapılandırmasını modele ekle.
PPO eğitimi için modeli value head ile kur.

Uygulamalı interaktif egzersiz

Bu örnek kodu tamamlayarak bu egzersizi bitirin.

# Set the configuration parameters
config = LoraConfig(
    r=32,  
    lora_alpha=32,  
    lora_dropout=____,  
    bias=____)  

# Apply the LoRA configuration to the 8-bit model
lora_model = get_peft_model(pretrained_model_8bit, ____)
# Set up the tokenizer and model with a value head for PPO training
model = ____.from_pretrained(____)

Kodu Düzenle ve Çalıştır

Bu egzersiz

İnsan Geri Bildiriminden Pekiştirmeli Öğrenme (RLHF)

kursunun bir parçasıdır

AvançadoNível de habilidade

4.8+

Kursa Ücretsiz Başlayın

This chapter introduces the basics of Reinforcement Learning with Human Feedback (RLHF), a technique that uses human input to help AI models learn more effectively. Get started with RLHF by understanding how it differs from traditional reinforcement learning and why human feedback can enhance AI performance in various domains.

Exercise 1: Introduction to RLHF Exercise 2: Text generation with RLHF Exercise 3: Classifying generated text for RLHF Exercise 4: RL vs. RLHF Exercise 5: Exploring pre-trained LLMs Exercise 6: Tokenize a text dataset Exercise 7: Fine-tuning for review classification Exercise 8: Preparing data for RLHF Exercise 9: Preparing the preference dataset Exercise 10: Extracting prompts

Discover how to set up systems for gathering human feedback in this Chapter. Learn best practices for collecting high-quality data, from pairwise comparisons to uncertainty sampling, and explore strategies for enhancing your data collection.

Exercise 1: Methods for high-quality feedback gathering Exercise 2: Understanding comparison and rating in RLHF Exercise 3: Comparing slogans for a gym campaign Exercise 4: Measuring feedback quality and relevance Exercise 5: Low confidence Exercise 6: K-means for feedback clustering Exercise 7: Active learning Exercise 8: Implementing an active learning pipeline Exercise 9: Active learning loop

In this Chapter, you'll get into the core of Reinforcement Learning from Human Feedback training. This includes exploring fine-tuning with PPO, techniques to train efficiently, and handling potential divergences from your metrics' objectives.

Exercise 1: Ödül modellerine derin bakış Exercise 2: Ödülü başlatma Exercise 3: Ödül eğitmenini ayarlama Exercise 4: PPO ile eğitim Exercise 5: PPO eğitmenini başlat Exercise 6: PPO ile ince ayar Exercise 7: RLHF'te verimli ince ayar Exercise 8: 8-bit Eğitime Hazırlık Exercise 9: LoRA ile eğit

Geçerli Egzersiz

Explore key techniques for assessing and improving model performance in this last Chapter of Reinforcement Learning from Human Feedback (RLHF): from fine-tuning metrics to incorporating diverse feedback sources, you'll be provided with a comprehensive toolkit to refine your models effectively.

Exercise 1: Model metrics and adjustments Exercise 2: Mitigating negative KL divergence Exercise 3: Checking the reward model Exercise 4: Incorporating diverse feedback sources Exercise 5: Majority voting on multiple data sources Exercise 6: Unreliable data source identification Exercise 7: Evaluating RLHF models Exercise 8: Interpreting curves Exercise 9: Evaluating RLHF with metrics Exercise 10: Wrapping up your RLHF journey