Nội dung khóa học
-
2
Week 1: Deep Learning Fundamentals
-
1.1_Slide_Deep Learning Fundamentals_16/03
-
1.1_Record_Deep Learning Fundamentals_16/03
-
1.1_Quiz_Deep Learning Fundamentals_Deadline 10/04
-
1.2_Record_HuggingFace Framework_20/3
-
1.2_Code_HuggingFace Framework_20/3
-
1.2_Quiz_HuggingFace Framework_Dealine 10/04/2025
-
-
3
Week 2: Introduction to LLMs Overview & Architectures
-
2.1_Slide_Introduction to LLMs Overview & Architectures_23/3
-
2.1_Record_Introduction to LLMs Overview & Architectures_23/3
-
2.1_Quiz_Introduction to LLMs Overview & Architectures_Dealine 14/04/2025
-
2.2_Record__LLM-focused introduction_30/3
-
2.2_Slide_LLM-focused introduction_30/3
-
2.2_Code_LLM-focused introduction_30/3
-
2.2_Quiz_LLM-focused introduction_Deadline 18/04/2025
-
-
4
Week 3: Train/Fine-tune your first model
-
3.1_Slide_Challenges Training Big Models_03/04
-
3.1_Record_Challenges Training Big Models_03/04
-
3.1_Quiz_Challenges Training Big Models_Deadline 03/05/2025
-
3.2.1_Slide_SFT for LLMs_06/04
-
3.2.2_Slide_SFT for LLMs_06/04
-
3.2.1_Code_SFT for LLMs_06/04
-
3.2.2_Code_Data Loading_06/04
-
3.2.3_Code_Train_06/04
-
3.2_Record_SFT for LLMs_06/04
-
3.2_Quiz_SFT for LLMs_Deadline 03/05/2025
-
-
5
Assignment 01: Token Modification
-
Assignment 01 Setup Tutorial
-
Assignment 01_Token Modification_Deadline 22/04/2025
-
-
6
Week 4: Train/Fine-tune your first model (cont.)
-
4.1.1_Slide_SFT for LLMs: Different approaches_10/04
-
4.1.2_Slide_SFT for LLMs: Different approaches_10/04
-
4.1_Quiz_SFT for LLMs: Different approaches_Deadline 26/05/2025
-
4.1_Record_SFT for LLMs: Different approaches_10/04
-
4.2_Code_ Parameter Efficient training_17/04
-
4.2_Record_ Parameter Efficient training_17/04
-
4.2_Quiz_ Parameter Efficient training_Deadline 26/05/2025
-
-
7
Week 5: Assignment Break
-
5.1_Record_TA Office hour_13/04
-
5.2_Record_TA Office hour_20/4
-
Link đăng ký đề tài và tài liệu_Deadline 24/04/2025
-
-
8
Week 6: Alignment to human preference (and beyond)
-
6.1_Slide_Reinforcement Learing in LLMs_24/4
-
6.1_Record_Reinforcement Learning in LLM_24/4
-
6.2_Slide_RLHF/DPO Coding_27/4
-
6.2_Code_RLHF/DPO Coding_27/4
-
6.2_Record_RLHF/DPO Coding_27/4
-
-
9
Week 7: Prompt engineering, Datasets and Evaluation
-
7.1_Slide_Prompt engineering_08/05
-
7.1_Record_Prompt Engineering_08/05
-
7.2_Slide_Synthetic and Data Evaluation_11/05
-
7.2_Record_Synthetic and Data Evaluation_11/05
-