Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,8 @@ datasets:
|
|
9 |
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).
|
10 |
Fine-tuned with first 100k rows from dataset with 1 epoch, it took around 2 hours 20 minutes with NVIDIA RTX 4090.
|
11 |
|
|
|
|
|
12 |
## Important Notes
|
13 |
- 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.
|
14 |
- Model is using bitsandbytes so use it with a CUDA supported GPU.
|
|
|
9 |
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).
|
10 |
Fine-tuned with first 100k rows from dataset with 1 epoch, it took around 2 hours 20 minutes with NVIDIA RTX 4090.
|
11 |
|
12 |
+
Model can now generate some good answers. But sometimes it can generate inappropriate answers. I think this problem is based on lack of data.
|
13 |
+
|
14 |
## Important Notes
|
15 |
- 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.
|
16 |
- Model is using bitsandbytes so use it with a CUDA supported GPU.
|