Made the README more descriptive.

README.md

@@ -2,7 +2,6 @@
 license: gemma
 library_name: transformers
 tags:
-- trl
 - sft
 - generated_from_trainer
 base_model: google/gemma-7b
@@ -15,38 +14,80 @@ datasets:
 language:
 - en
 widget:
-- text: "Quote: With great power comes"
-  example_title: "Example 1"
-- text: "Quote: Hasta la vista baby"
-  example_title: "Example 2"
-- text: "Quote: Elementary, my dear watson."
-  example_title: "Example 3"
+- text: 'Quote: With great power comes'
+  example_title: Example 1
+- text: 'Quote: Hasta la vista baby'
+  example_title: Example 2
+- text: 'Quote: Elementary, my dear watson.'
+  example_title: Example 3
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# outputs
+# Gemma_ft_Quote
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the [english quote](https://huggingface.co/datasets/Abirate/english_quotes) dataset using [LoRA](https://arxiv.org/abs/2106.09685).
+It is based on the example provided by google [here](https://huggingface.co/google/gemma-7b/blob/main/examples/notebook_sft_peft.ipynb).
+The notebook used to fine-tune the model can be found [here](https://colab.research.google.com/drive/1OMvXuK77X7yxofrhQHERUkrn3NZORXFp?usp=sharing)
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset.
 
 ## Model description
 
-More information needed
+The model can complete popular quotes given to it and add the author of the quote. For example, Given the qoute below:
+
+```
+Quote: With great power comes
+```
+
+The model would complete the quote and add the author of the quote:
+
+```
+Quote: With great power comes great responsibility. Author: Ben Parker.
+```
+
+Given a complete Quoute the model would add the author:
+
+```
+Quote: I'll be back. Author: Arnold Schwarzenegger.
+```
+
+## Usage
 
-## Intended uses & limitations
+The model can be used with [transformers](https://huggingface.co/docs/transformers/en/index) library. Here's an example of loading the model
+in 4 bit quantization mode:
 
-More information needed
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
-## Training and evaluation data
+model_id = "Eteims/gemma_ft_quote"
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
 
-More information needed
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map="cuda:0")
+```
 
-## Training procedure
+This code would easily run in a free colab tier.
+
+After loading the model you can use it for inference:
+
+```python
+text = "Quote: Elementary, my dear watson."
+device = "cuda:0"
+inputs = tokenizer(text, return_tensors="pt").to(device)
+
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
 ### Training hyperparameters
 
-The following hyperparameters were used during training:
+The following hyperparameters were used during fine-tuning:
 - learning_rate: 0.0002
 - train_batch_size: 1
 - eval_batch_size: 8
@@ -59,10 +100,6 @@ The following hyperparameters were used during training:
 - training_steps: 10
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.8.2