File size: 1,376 Bytes
38301fe 92c050e 38301fe 3c5cfdf 38301fe 3c5cfdf |
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 53 54 55 56 |
---
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- code
---
# Phi-2-super (SFT + cDPO)
Base Model: [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ceeb27e7f6014c0e9d9268/5-LQCMrXi8FN_ewcWL47v.png)
How to run inference:
```python
import transformers
import torch
if __name__ == "__main__":
model_name = "abacaj/phi-2-super"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
model = (
transformers.AutoModelForCausalLM.from_pretrained(
model_name,
)
.to("cuda:0")
.eval()
)
messages = [
{"role": "user", "content": "Hello, who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
input_ids_cutoff = inputs.size(dim=1)
with torch.no_grad():
generated_ids = model.generate(
input_ids=inputs,
use_cache=True,
max_new_tokens=512,
temperature=0.2,
top_p=0.95,
do_sample=True,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
)
completion = tokenizer.decode(
generated_ids[0][input_ids_cutoff:],
skip_special_tokens=True,
)
print(completion)
``` |