Update README.md

README.md

@@ -1,3 +1,46 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+## How to use
+
+This instructed model uses a chat template that must be adhered to the input for conversational use.
+The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
+
+model_id = "BSC-LT/salamandra7b_rag_prompt_ca-en-es"
+
+prompt = "Here is a question that you should answer based on the given context. Write a response that answers the question using only information provided in the context. Provide the answer in Spanish."
+
+context = """Water boils at 100°C (212°F) at standard atmospheric pressure, which is at sea level.
+However, this boiling point can vary depending on altitude and atmospheric pressure.
+At higher altitudes, where atmospheric pressure is lower, water boils at a lower temperature.
+For example, at 2,000 meters (about 6,600 feet) above sea level, water boils at around 93°C (199°F).
+"""
+instruction = "At what temperature does water boil?"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="cuda",
+    torch_dtype=torch.bfloat16
+  )
+
+content = f"{prompt}\n\nContext:\n{context}\n\nQuestion:\n{instruction}"
+chat = [ { "role": "user", "content": content } ]
+
+prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+
+eos_tokens = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|im_end|>"),
+  ]
+
+inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
+outputs = model.generate(input_ids=inputs.to(model.device), eos_token_id=eos_tokens, max_new_tokens=200)
+
+```