Update README.md

README.md

@@ -35,12 +35,35 @@ This model is a fine-tuned version of [SGaleshchuk/Llama-2-13b-hf_uk_rank-32_ft]
 
 
 ## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
+```python
+# unpatch flash attention
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+# load base LLM model and tokenizer
+model = AutoPeftModelForCausalLM.from_pretrained(
+  "SGaleshchuk/Llama-2-13b-summarization_uk_dpo",
+  low_cpu_mem_usage=True,
+  torch_dtype=torch.float16,
+  load_in_4bit=True)
+
+tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
+
+for instruct, summary in zip(val_instructions, tqdm(summaries)):
+    input_ids = tokenizer(
+       instruct, return_tensors="pt", truncation=True).input_ids.cuda()
+    with torch.inference_mode():
+        outputs = model.generate(
+                input_ids=input_ids,
+                max_new_tokens=128,
+                do_sample=True,
+                top_p=0.9,
+                temperature=1e-2,
+            )
+        result = tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]
+        result = result[len(instruct) :]
+        print(result)
+```
 
 ## Training procedure