chriscelaya commited on
Commit
57e5877
·
verified ·
1 Parent(s): ebca243

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -1
README.md CHANGED
@@ -16,6 +16,7 @@ language:
16
  This repository demonstrates how to fine-tune the **Qwen 7B** model to create "Andy," an AI assistant for Minecraft. Using the **Unsloth framework**, this tutorial showcases efficient fine-tuning with 4-bit quantization and LoRA for scalable training on limited hardware.
17
 
18
  ## 🚀 Resources
 
19
  - **Source Code**: [GitHub Repository](https://github.com/while-basic/mindcraft)
20
  - **Colab Notebook**: [Colab Notebook](https://colab.research.google.com/drive/1Eq5dOjc6sePEt7ltt8zV_oBRqstednUT?usp=sharing)
21
  - **Blog Article**: [Walkthrough](https://chris-celaya-blog.vercel.app/articles/unsloth-training)
@@ -34,6 +35,7 @@ This **readme.md** provides step-by-step instructions to:
34
  ---
35
 
36
  ### Key Features
 
37
  - **Memory-Efficient Training**: Fine-tune large models on GPUs as low as T4 (Google Colab).
38
  - **LoRA Integration**: Modify only key model layers for efficient domain-specific adaptation.
39
  - **Minecraft-Optimized Dataset**: Format data using **ChatML templates** for seamless integration.
@@ -42,6 +44,7 @@ This **readme.md** provides step-by-step instructions to:
42
  ---
43
 
44
  ## Prerequisites
 
45
  - **Python Knowledge**: Familiarity with basic programming concepts.
46
  - **GPU Access**: T4 (Colab Free Tier) is sufficient; higher-tier GPUs like V100/A100 recommended.
47
  - **Optional**: [Hugging Face Account](https://huggingface.co/) for model sharing.
@@ -156,6 +159,7 @@ model.save_pretrained("andy_minecraft_assistant")
156
  ---
157
 
158
  ## Optimization Tips
 
159
  - Expand the dataset for broader Minecraft scenarios.
160
  - Adjust training steps for better accuracy.
161
  - Fine-tune inference parameters for more natural responses.
@@ -164,4 +168,16 @@ model.save_pretrained("andy_minecraft_assistant")
164
 
165
  For more details on **Unsloth** or to contribute, visit [Unsloth GitHub](https://github.com/unslothai/unsloth).
166
 
167
- Happy fine-tuning! 🎮
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  This repository demonstrates how to fine-tune the **Qwen 7B** model to create "Andy," an AI assistant for Minecraft. Using the **Unsloth framework**, this tutorial showcases efficient fine-tuning with 4-bit quantization and LoRA for scalable training on limited hardware.
17
 
18
  ## 🚀 Resources
19
+
20
  - **Source Code**: [GitHub Repository](https://github.com/while-basic/mindcraft)
21
  - **Colab Notebook**: [Colab Notebook](https://colab.research.google.com/drive/1Eq5dOjc6sePEt7ltt8zV_oBRqstednUT?usp=sharing)
22
  - **Blog Article**: [Walkthrough](https://chris-celaya-blog.vercel.app/articles/unsloth-training)
 
35
  ---
36
 
37
  ### Key Features
38
+
39
  - **Memory-Efficient Training**: Fine-tune large models on GPUs as low as T4 (Google Colab).
40
  - **LoRA Integration**: Modify only key model layers for efficient domain-specific adaptation.
41
  - **Minecraft-Optimized Dataset**: Format data using **ChatML templates** for seamless integration.
 
44
  ---
45
 
46
  ## Prerequisites
47
+
48
  - **Python Knowledge**: Familiarity with basic programming concepts.
49
  - **GPU Access**: T4 (Colab Free Tier) is sufficient; higher-tier GPUs like V100/A100 recommended.
50
  - **Optional**: [Hugging Face Account](https://huggingface.co/) for model sharing.
 
159
  ---
160
 
161
  ## Optimization Tips
162
+
163
  - Expand the dataset for broader Minecraft scenarios.
164
  - Adjust training steps for better accuracy.
165
  - Fine-tune inference parameters for more natural responses.
 
168
 
169
  For more details on **Unsloth** or to contribute, visit [Unsloth GitHub](https://github.com/unslothai/unsloth).
170
 
171
+ Happy fine-tuning! 🎮
172
+
173
+ ## Citation
174
+
175
+ @misc{celaya2025minecraft,
176
+ author = {Christopher B. Celaya},
177
+ title = {Efficient Fine-Tuning of Large Language Models - A Minecraft AI Assistant Tutorial},
178
+ year = {2025},
179
+ publisher = {GitHub},
180
+ journal = {GitHub repository},
181
+ howpublished = {\url{https://github.com/kolbytn/mindcraft}},
182
+ note = {\url{https://chris-celaya-blog.vercel.app/articles/unsloth-training}}
183
+ }