Update README.md

README.md

@@ -4,21 +4,23 @@ language:
 - en
 - fa
 pipeline_tag: text-generation
-tags:
-- PartAI
 ---
 
 # Model Details
 
-The Dorna models are a family of decoder-only models, specifically trained/fine-tuned on Persian data, developed by [Part AI](https://partdp.ai/). As an initial release, an 8B instruct model from this family is being made available.
-Dorna-Llama3-8B-Instruct is built using the [Meta Llama 3 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) model.
+This Repository is a 4-bit quantized version of [Dorna-Llama3-8B-Instruct](https://huggingface.co/PartAI/Dorna-Llama3-8B-Instruct) model for efficient memory usage. Dorna model is a decoder-only model, specifically trained/fine-tuned on Persian data. [Flash Attention 2](https://arxiv.org/abs/2307.08691) is also integrated for faster inference.
 
+## Benefits
 
-## How to use
+- **Reduced Memory Usage**: 4-bit quantization lowers memory requirements.
+- **Faster Inference**: Flash Attention 2 speeds up processing.
+- **Easy Deployment**: No need for additional libraries like LlamaCPP or Candle.
+- **Ready to Use**: Compatible with Langchain, Haystack, LlamaIndex 2, and more.
+- **Google Colab Friendly**: Can run on Google Colab free tier with T4 GPU (less than 15 GB of GPU RAM).
 
-To test and use model freely on Hugging Face Spaces click [here](https://huggingface.co/spaces/PartAI/Dorna-Llama3-8B-Instruct)!
+## How to use
 
-You can also run conversational inference using the Transformers Auto classes with the `generate()` function. Let's look at an example.
+You can run conversational inference using the Transformers Auto classes with the `generate()` function. Let's look at an example.
 
 ```Python
 import torch
@@ -36,7 +38,7 @@ model = AutoModelForCausalLM.from_pretrained(
 messages = [
     {"role": "system",
      "content": "You are a helpful Persian assistant. Please answer questions in the asked language."},
-    {"role": "user", "content": "کاغذ A4 بزرگ تر است یا A5؟"},
+    {"role": "user", "content": "اصفهان بزرگ تر است یا قم؟"},
 ]
 
 input_ids = tokenizer.apply_chat_template(
@@ -62,12 +64,7 @@ response = outputs[0][input_ids.shape[-1]:]
 print(tokenizer.decode(response, skip_special_tokens=True))
 ```
 
-You can also use the notebook below to test the model in Google Colab.
-
-<a href="https://colab.research.google.com/drive/1TmeZsN4Byi1EgAEQeOt27sPrZOWn5gBH?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab Code" width="87" height="15"/></a>
-
-
-## Evaluation
+## Evaluation of Non-Quantized version
 
 This model is evaluated on questions across various tasks, including Boolean Questions, Code Generation, Long Response, Math, News QA, Paraphrasing, General Knowledge, and Summarization. Most categories typically have two main difficulty levels: Hard and Easy.
 
@@ -193,4 +190,4 @@ Automatic evaluation results are as follows:
 
 ## Contact us
 
-If you have any questions regarding this model, you can reach us via the [community](https://huggingface.co/PartAI/Dorna-Llama3-8B-Instruct/discussions) on Hugging Face.
+If you have any questions regarding this model, you can reach us via the [community](https://huggingface.co/amirMohammadi/Dorna-Llama3-8B-Instruct-Quantized4Bit/discussions) on Hugging Face.