Update README.md

README.md

@@ -260,6 +260,41 @@ All training artifacts are publicly available:
 
 ## Usage Examples
 
+### Quantization
+<details>
+<summary>Click to expand <strong>encoder</strong> usage examples</summary>
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+quantization_config = BitsAndBytesConfig(
+    load_in_8bit=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/ettin-decoder-1b")
+model = AutoModelForCausalLM.from_pretrained(
+    "jhu-clsp/ettin-decoder-1b",
+    torch_dtype=torch.float16,
+    device_map="auto",
+    quantization_config=quantization_config
+)
+
+prompt = "The future of artificial intelligence is"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_length=50,
+        num_return_sequences=1,
+        temperature=0.7,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(f"Generated text: {generated_text}")
+</summary>
+
 ### Encoder: Masked Language Modeling
 <details>
 <summary>Click to expand <strong>encoder</strong> usage examples</summary>