File size: 1,233 Bytes
8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 45d2cb3 8bfd3a6 |
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 |
---
tags:
- autotrain
- text-generation-inference
- text-generation
- peft
library_name: transformers
widget:
- messages:
- role: user
content: What is your favorite condiment?
license: other
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```bash
pip install peft
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import AutoPeftModelForCausalLM, PeftConfig
model_id = "Aryan-401/phi-3-mini-4k-instruct-finetune-guanaco"
peft_model=AutoPeftModelForCausalLM.from_pretrained(model_id)
model = peft_model.merge_and_unload()
tokenizer = AutoTokenizer.from_pretrained(model_id)
messages = [
{"role": "user", "content": "What is the Value of Pi?"}
]
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device).eval()
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to(device), max_length= 1000)
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
print(response)
``` |