Sweaterdog
commited on
Commit
•
b634819
1
Parent(s):
c6fb203
Update README.md
Browse files
README.md
CHANGED
@@ -17,6 +17,26 @@ language:
|
|
17 |
- **License:** apache-2.0
|
18 |
- **Finetuned from model :** unsloth/Qwen2.5-7B-bnb-4bit
|
19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
17 |
- **License:** apache-2.0
|
18 |
- **Finetuned from model :** unsloth/Qwen2.5-7B-bnb-4bit
|
19 |
|
20 |
+
The MindCraft LLM tuning CSV file can be found here, this can be tweaked as needed. [MindCraft-LLM](https://huggingface.co/datasets/Sweaterdog/MindCraft-LLM-tuning/raw/main/Gemini-Minecraft%20-%20training_data_minecraft_updated.csv)
|
21 |
+
|
22 |
+
# What is the Purpose?
|
23 |
+
|
24 |
+
This model is built and designed to play Minecraft via the extension named "[MindCraft](https://github.com/kolbytn/mindcraft)" Which allows language models, like the ones provided in the files section, to play Minecraft.
|
25 |
+
- Why a new model?
|
26 |
+
#
|
27 |
+
While, yes, models that aren't fine tuned to play Minecraft *Can* play Minecraft, most are slow, innaccurate, and not as smart, in the fine tuning, it expands reasoning, conversation examples, and command (tool) usage.
|
28 |
+
- What kind of Dataset was used?
|
29 |
+
#
|
30 |
+
I'm deeming this model *"Hermes"*, it was trained for reasoning by using examples of in-game "Vision" as well as examples of spacial reasoning, for expanding thinking, I also added puzzle examples where the model broke down the process step by step to reach the goal.
|
31 |
+
- Why choose Qwen2.5 for the base model?
|
32 |
+
#
|
33 |
+
During testing, to find the best local LLM for playing Minecraft, I came across two, Gemma 2, and Qwen2.5, these two were by far the best at playing Minecraft before fine-tuning, and I knew, once tuned, it would become better.
|
34 |
+
|
35 |
+
|
36 |
+
Here is the link to the Google Colab notebook for fine tuning your own model, in case you want to use a different one, such as Llama-3-8b, or if you want to change the hyperparameters
|
37 |
+
[Google Colab](https://colab.research.google.com/drive/1ZoP7vO50kQrtHoQ54EI6URnoWzIJUg-c?usp=sharing)
|
38 |
+
|
39 |
+
#
|
40 |
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
41 |
|
42 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|