Instructions to use chriscelaya/minecraft-ai-training-tutorial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chriscelaya/minecraft-ai-training-tutorial with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("chriscelaya/minecraft-ai-training-tutorial", dtype="auto")

llama-cpp-python

How to use chriscelaya/minecraft-ai-training-tutorial with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="chriscelaya/minecraft-ai-training-tutorial",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use chriscelaya/minecraft-ai-training-tutorial with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chriscelaya/minecraft-ai-training-tutorial:Q4_K_M

Use Docker

docker model run hf.co/chriscelaya/minecraft-ai-training-tutorial:Q4_K_M

LM Studio
Jan
Ollama
How to use chriscelaya/minecraft-ai-training-tutorial with Ollama:
```
ollama run hf.co/chriscelaya/minecraft-ai-training-tutorial:Q4_K_M
```

Unsloth Studio new

How to use chriscelaya/minecraft-ai-training-tutorial with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for chriscelaya/minecraft-ai-training-tutorial to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for chriscelaya/minecraft-ai-training-tutorial to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for chriscelaya/minecraft-ai-training-tutorial to start chatting

Docker Model Runner
How to use chriscelaya/minecraft-ai-training-tutorial with Docker Model Runner:
```
docker model run hf.co/chriscelaya/minecraft-ai-training-tutorial:Q4_K_M
```

Lemonade

How to use chriscelaya/minecraft-ai-training-tutorial with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chriscelaya/minecraft-ai-training-tutorial:Q4_K_M

Run and chat with the model

lemonade run user.minecraft-ai-training-tutorial-Q4_K_M

List all available models

lemonade list

chriscelaya commited on Jan 22, 2025

Commit

81ae74c

verified ·

1 Parent(s): c12e025

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -17,11 +17,13 @@ This repository demonstrates how to fine-tune the **Qwen 7B** model to create "A
 ## 🚀 Resources
 - **Source Code**: [GitHub Repository](https://github.com/while-basic/mindcraft)  #todo: add mindcraft repo
-- **Colab Notebook**: [Run the Tutorial](https://colab.research.google.com/drive/1Eq5dOjc6sePEt7ltt8zV_oBRqstednUT?usp=sharing)  #todo: add colab notebook url
 ## Overview
-This guide provides step-by-step instructions to:
 1. Install and set up the **Unsloth framework**.
 2. Initialize the **Qwen 7B** model with **4-bit quantization**.
 3. Implement **LoRA Adapters** for memory-efficient fine-tuning.
@@ -67,7 +69,7 @@ import torch
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name="unsloth/Qwen2.5-7B-bnb-4bit",
     max_seq_length=2048,
-    dtype=torch.bfloat16,  # Or torch.float16 for older GPUs
     load_in_4bit=True,
     trust_remote_code=True,
 )

 ## 🚀 Resources
 - **Source Code**: [GitHub Repository](https://github.com/while-basic/mindcraft)  #todo: add mindcraft repo
+- **Colab Notebook**: [Colab Notebook](https://colab.research.google.com/drive/1Eq5dOjc6sePEt7ltt8zV_oBRqstednUT?usp=sharing)
+- **Blog Article**: [Walkthrough](https://chris-celaya-blog.vercel.app/articles/unsloth-training)
+- **Teaser**: [Video](https://www.youtube.com/watch?v=KUXY5OtaPZc)
 ## Overview
+This **readme.md** provides step-by-step instructions to:
 1. Install and set up the **Unsloth framework**.
 2. Initialize the **Qwen 7B** model with **4-bit quantization**.
 3. Implement **LoRA Adapters** for memory-efficient fine-tuning.
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name="unsloth/Qwen2.5-7B-bnb-4bit",
     max_seq_length=2048,
+    dtype=torch.bfloat16,
     load_in_4bit=True,
     trust_remote_code=True,
 )