Update README.md

README.md

@@ -8,9 +8,11 @@ pipeline_tag: text-generation
 
 # Model Card for Model ID
 
-Introducing Pixie Zehir Nano
-Excelling in writing
-Fine tuned on HQ DATA™ from Pixie Zehir.
+  Introducing Pixie Zehir Nano
+  
+  Excelling in writing
+  
+  Fine tuned on HQ DATA™ from Pixie Zehir.
 
 ## Model Details
 
@@ -24,3 +26,34 @@ Fine tuned on HQ DATA™ from Pixie Zehir.
 
 Model is created for research purposes, it can and will hallucinate, use with caution.
 
+## Usage
+
+```bash
+pip install transformers==4.36.1
+```
+
+```python
+import torch
+from transformers import pipeline
+pipe = pipeline(
+    "text-generation",
+    model="h2oai/h2o-danube-1.8b-chat",
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+# We use the HF Tokenizer chat template to format each message
+# https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [
+    {"role": "user", "content": "Why is drinking water so healthy?"},
+]
+prompt = pipe.tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+res = pipe(
+    prompt,
+    max_new_tokens=256,
+)
+print(res[0]["generated_text"])
+# <|prompt|>Write a haiku.</s><|answer|> In the windowless room, Digital dreams consume, Unseen sun sets on a white rabbit's ears: [...]