Update README.md

README.md

@@ -117,17 +117,46 @@ It achieves the following results on the evaluation set:
 - Loss: 0.0695
 - F1 Score: 83.14
 
+For more details, see my [article](https://simmering.dev/open-absa)
+
+## Intended uses & limitations
+
+Aspect-based sentiment analysis in English. Pass it review sentences wrapped in tags, like this: [INST]The cheeseburger was tasty but the fries were soggy.[/INST]
+
+## How to run
+
 This adapter requires that two new tokens are added to the tokenizer. The tokens are: "[INST]" and "[/INST]". Also, the base model's embedding layer size has to be increased by 2.
 
-For more details, see my [article](https://simmering.dev/open-absa)
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-## Model description
+extra_tokens = ["[INST]", "[/INST]"]
+base_model = "NousResearch/Meta-Llama-3-8B"
 
-More information needed
+base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Meta-Llama-3-8B")
+base_model.resize_token_embeddings(base_model.config.vocab_size + len(extra_tokens))
 
-## Intended uses & limitations
+tokenizer = AutoTokenizer.from_pretrained("NousResearch/Meta-Llama-3-8B")
 
-Aspect-based sentiment analysis in English. Pass it review sentences wrapped in tags, like this: [INST]The cheeseburger was tasty but the fries were soggy.[/INST]
+tokenizer.add_special_tokens({"additional_special_tokens": extra_tokens})
+
+model = PeftModel.from_pretrained(base_model, "psimm/llama-3-8B-semeval2014")
+
+input_text = "[INST]The food was tasty[/INST]"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids
+
+gen_tokens = model.generate(
+    input_ids,
+    max_length=256,
+    temperature=0.01,
+)
+
+# Remove the input tokens
+output_tokens = gen_tokens[:, input_ids.shape[1] :]
+
+print(tokenizer.batch_decode(output_tokens, skip_special_tokens=True))
+```
 
 ## Training and evaluation data