Update README.md

README.md

@@ -4,23 +4,52 @@ language:
 license: apache-2.0
 tags:
 - chat
-- mlx
+- code
 pipeline_tag: text-generation
+datasets:
+- YashJain/GitAI
+library_name: transformers
 ---
 
 # YashJain/GitAI-Qwen2-0.5B-Instruct
 
-The Model [YashJain/GitAI-Qwen2-0.5B-Instruct](https://huggingface.co/YashJain/GitAI-Qwen2-0.5B-Instruct) was converted to MLX format from [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) using mlx-lm version **0.15.0**.
 
-## Use with mlx
-
-```bash
-pip install mlx-lm
+## Requirements
+The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
 ```
-
+KeyError: 'qwen2'
+```
+## Quickstart
 ```python
-from mlx_lm import load, generate
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # the device to load the model onto
 
-model, tokenizer = load("YashJain/GitAI-Qwen2-0.5B-Instruct")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
-```
+model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2-0.5B-Instruct",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```