File size: 1,445 Bytes
2617037 b20adcd c44ed87 b20adcd 4be7659 b20adcd 3f845c5 2617037 b20adcd e68057c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
---
library_name: transformers
tags: []
widget:
- example_title: EMO 1
messages:
- role: system
content: You are a helpful 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?
inference:
parameters:
max_new_tokens: 500
---
# 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 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)
```
|