Update README.md

README.md

@@ -4,14 +4,18 @@ datasets:
 - timdettmers/openassistant-guanaco
 pipeline_tag: text-generation
 ---
-Model fine-tuned in 4-bit precision using QLoRA on [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) with weights merged after training.
 
-Made using this [Google Colab notebook](https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing).
+📝 [Article](https://towardsdatascience.com/fine-tune-your-own-llama-2-model-in-a-colab-notebook-df9823a04a32) |
+💻 [Colab](https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing)
 
-It can be easily imported using the `AutoModelForCausalLM` class from `transformers`:
+This is a Llama 2-7b model QLoRA fine-tuned (4-bit precision) on the [`mlabonne/guanaco-llama2-1k`](https://huggingface.co/datasets/mlabonne/guanaco-llama2) dataset.
+
+It was trained on a Google Colab notebook with a T4 GPU and high RAM. It is mainly designed for educational purposes, not for inference.
+
+You can easily import it using the `AutoModelForCausalLM` class from `transformers`:
 
 ```
 from transformers import AutoModelForCausalLM
 
-model = AutoModelForCausalLM("mlabonne/llama-2-7b-guanaco")
+model = AutoModelForCausalLM("mlabonne/llama-2-7b-miniguanaco")
 ```