Sweaterdog
commited on
Commit
•
4782668
1
Parent(s):
6e8d337
Update README.md
Browse files
README.md
CHANGED
@@ -64,7 +64,31 @@ In order to use this model, A, download the GGUF file of the version you want, e
|
|
64 |
|
65 |
8.In the CMD window, type "ollama run Hermes1" (replace the 1 in Hermes with whatever version you downloaded)
|
66 |
|
67 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
I'm aware it does say there are multiple Qwen2.5 files, even though there are two, and it also says there are Gemma2 models, even though there isn't, I am aware and have been trying to train the rest of these models.
|
70 |
|
|
|
64 |
|
65 |
8.In the CMD window, type "ollama run Hermes1" (replace the 1 in Hermes with whatever version you downloaded)
|
66 |
|
67 |
+
# How to fine tune a Gemini Model
|
68 |
+
1. Download the CSV for [MindCraft-LLM-tuning](https://huggingface.co/datasets/Sweaterdog/MindCraft-LLM-tuning)
|
69 |
+
2. Open sheet.google.com, and upload the CSV file
|
70 |
+
3. Go to [API keys and Services](https://aistudio.google.com/app/apikey), then click on "New Tuned Model" on the left popup bar
|
71 |
+
4. Press "Import" and then select the CSV file you uploaded to google sheets
|
72 |
+
5. Rename the model to whatever you want, set the training settings, epochs, learning rate, and batch size
|
73 |
+
6. Change the model to either Gemini-1.0-pro or Gemini-1.5-flash **NOTE** Gemini 1.0 pro will be deprecated on February 15, 2025, meaning the model WILL BE deleted!
|
74 |
+
7. Hit tune and wait.
|
75 |
+
8. After the model is finished training, hit "Add API access" and select the google project you'd like to connect it to
|
76 |
+
9. Copy the model ID, and paste it into the Gemini.json file in MindCraft, then name the model to whatever you want.
|
77 |
+
10. (Optional) Test the model by pressing "Use in chat" and ask it basic actions, such as "Grapevine_eater: Come here!" and see the output, if it is not to your liking, train the model again with different settings,
|
78 |
+
11. (Optional) Since the rates for Gemini models are limited (If you do not have billing enabled) I recommend making a launch.bat file in the MindCraft folder, instead of crashing and having you need to manually start the program every time the rate limit is reached. Here is the code I use in launch.bat
|
79 |
+
```
|
80 |
+
@echo off
|
81 |
+
setlocal enabledelayedexpansion
|
82 |
+
|
83 |
+
:loop
|
84 |
+
node main.js
|
85 |
+
timeout /t 10 /nobreak
|
86 |
+
|
87 |
+
echo Restarting...
|
88 |
+
goto loop
|
89 |
+
```
|
90 |
+
12. Enjoy having a model play Minecraft with you, hopefully it is smarter than regular Gemini models!
|
91 |
+
#
|
92 |
|
93 |
I'm aware it does say there are multiple Qwen2.5 files, even though there are two, and it also says there are Gemma2 models, even though there isn't, I am aware and have been trying to train the rest of these models.
|
94 |
|