Update README.md

README.md

@@ -1,8 +1,60 @@
----
+readme_content = """---
+language:
+- en
+license: llama3
+library_name: transformers
 tags:
-- llama3
+- nlp
 - text-generation
+- llama-3
+pipeline_tag: text-generation
 ---
 
-# My Custom Llama 3 Model
-This is a custom upload of the Llama 3 8B Instruct model.
+# Llama 3 8B Instruct
+
+This repository contains the weights for the Llama 3 8B Instruct model. It is optimized for chat and instruction-following tasks.
+
+## Model Details
+- **Architecture:** Llama 3
+- **Size:** 8B Parameters
+- **Type:** Instruction Tuned
+- **Library:** Transformers
+
+## How to use
+
+You can use this model directly with the Hugging Face `transformers` library:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "maherghanem86/llama3"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Hello, how are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))