Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,13 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
base_model: unsloth/gemma-1.1-7b-it-bnb-4bit
|
|
|
|
|
|
|
| 4 |
---
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
|
| 7 |
-
-
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
base_model: unsloth/gemma-1.1-7b-it-bnb-4bit
|
| 4 |
+
datasets:
|
| 5 |
+
- naklecha/minecraft-question-answer-700k
|
| 6 |
---
|
| 7 |
+
# Gemma 1.1 7B Instruct Minecraft Adapter Model
|
| 8 |
+
This model is fine-tuned from [Unsloth's Gemma 1.1 7B Instruct quantized model](https://huggingface.co/unsloth/gemma-1.1-7b-it-bnb-4bit) with [naklecha's Minecraft Question-Answer dataset](https://huggingface.co/datasets/naklecha/minecraft-question-answer-700k).
|
| 9 |
+
Fine-tuned with 500 steps, it took around 20 minutes with NVIDIA L4. I will share the notebook when model is finished.
|
| 10 |
|
| 11 |
+
## Important Notes
|
| 12 |
+
- Model sometimes generates answers with no meanings. I am currently investigating this. This process can be long since I am a beginner in this field. If you have any suggestions, feel free to say it on model's Community page.
|
| 13 |
+
- Model is using bitsandbytes so use it with a CUDA supported GPU.
|