|
--- |
|
library_name: transformers |
|
tags: [] |
|
widget: |
|
- example_title: EMO 1 |
|
messages: |
|
- role: system |
|
content: You are a helpful and emotional assistant that will always respond in EMO style. |
|
- role: user |
|
content: Imagine you're helping someone who is feeling overhelmed. How do you feel in this situation? |
|
- example_title: EMO 2 |
|
messages: |
|
- role: system |
|
content: You are a helpful and emotional assistant that will always respond in EMO style. |
|
- role: user |
|
content: My best friend recently lost their parent to cancer after a long battle. They are understandably devastated and struggling with grief. |
|
inference: |
|
parameters: |
|
max_new_tokens: 1024 |
|
do_sample: True |
|
--- |
|
|
|
# Model card comming soon |
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
device = "cuda" # the device to load the model onto |
|
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
"Abhaykoul/EMO-1B", |
|
torch_dtype="auto", |
|
device_map="auto" |
|
) |
|
tokenizer = AutoTokenizer.from_pretrained("Abhaykoul/EMO-1B") |
|
|
|
prompt = "Imagine you're helping someone who is feeling overwhelmed. How do you feel in this situation?" |
|
messages = [ |
|
{"role": "system", "content": "You are a helpful and emotional assistant that will always respond in EMO style"}, |
|
{"role": "user", "content": prompt} |
|
] |
|
text = tokenizer.apply_chat_template( |
|
messages, |
|
tokenize=False, |
|
add_generation_prompt=True |
|
) |
|
model_inputs = tokenizer([text], return_tensors="pt").to(device) |
|
|
|
generated_ids = model.generate( |
|
model_inputs.input_ids, |
|
max_new_tokens=512 |
|
) |
|
generated_ids = [ |
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) |
|
] |
|
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] |
|
print(response) |
|
``` |
|
|