## Run the model

### Instruction format
The template used to build a prompt for this Instruct model is defined as follows:

```
### USER:
{instruction1}
### RESPONSE:
{respone1}
### USER:
{instruction2}
### RESPONSE:
{respone2}
```

Run the model with the transformers library:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "tktung/MultiSV_Mixtral-8x7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,
                                             device_map="auto",
                                             dtype=torch.float16 # optional, load in 16-bit precision mode to reduce memory usage
                                            )
model.eval()

def make_prompt(instruction):
    return f"""### USER:
{instruction}
### RESPONSE:
"""

user_input = "Känner du till WARA M&L?"
input_prompt = make_prompt(user_input)
input_ids = tokenizer(input_prompt, return_tensors="pt")["input_ids"]
generated_token_ids = model.generate(
    inputs=input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.6,
    top_p=1,
)[0]
generated_text = tokenizer.decode(generated_token_ids)
```

### Retrieval Augmented Generation
The model was trained with the following prompt format for RAG:

Vietnamese:
```
### USER:
Sử dụng ngữ cảnh sau để trả lời câu hỏi ở cuối:
{context}
Câu hỏi: {human_prompt}
### RESPONSE:
```

Swedish:
```
### USER:
Använd följande sammanhang för att svara på frågan:
{context}
Fråga: {human_prompt}
### RESPONSE:
```