Add sample usage and license to model card

README.md

@@ -1,16 +1,17 @@
 ---
+base_model:
+- mistralai/Mistral-7B-v0.3
 language:
 - pt
+library_name: transformers
 metrics:
 - accuracy
-base_model:
-- mistralai/Mistral-7B-v0.3
 pipeline_tag: text-generation
-library_name: transformers
 tags:
 - legal
 - portuguese
 - Brazil
+license: cc-by-4.0
 ---
 
 # Juru: Legal Brazilian Large Language Model from Reputable Sources
@@ -19,12 +20,35 @@ This repository hosts the public checkpoints for **Juru-7B**, a Mistral-7B speci
 
 ## Checkpoints
 
-* Checkpoints were saved every **200** optimization steps up to step **3,800**.  
-* Each 200 step interval adds **~0.4 billion** tokens of continued pretraining.
-* We refer to **Juru-7B** as checkpoint **3,400** (~7.1 billion tokens), which achieved the best score on our Brazilian legal knowledge benchmarks.
+*   Checkpoints were saved every **200** optimization steps up to step **3,800**.  
+*   Each 200 step interval adds **~0.4 billion** tokens of continued pretraining.
+*   We refer to **Juru-7B** as checkpoint **3,400** (~7.1 billion tokens), which achieved the best score on our Brazilian legal knowledge benchmarks.
 
 > **Note:** The model has **not** been instruction finetuned. For best results, use few-shot inference or perform additional finetuning on your specific task.
 
+## Usage
+
+You can use the model with the `transformers` library:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "juru-llm/Juru-7B" 
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+# Ensure to use appropriate dtype for large models, e.g., torch.bfloat16 or torch.float16
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+
+prompt = "Qual é o prazo para apresentação de defesa em um processo judicial no Brasil?"
+input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+# Generate response
+# Adjust generation parameters like max_new_tokens, do_sample, top_p, temperature as needed.
+outputs = model.generate(**input_ids, max_new_tokens=100, do_sample=True, top_p=0.9, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
 ## Citation information
 
 ```bibtex