File size: 1,353 Bytes
3de7dd2 8cd99a2 3de7dd2 8cd99a2 999e3b4 8cd99a2 b2f4e75 8cd99a2 b2f4e75 8cd99a2 b2f4e75 8cd99a2 b2f4e75 8cd99a2 b2f4e75 8cd99a2 b2f4e75 8cd99a2 |
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 |
---
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
```python
!pip install -U "huggingface_hub[cli]"
!huggingface-cli login --token "************" --add-to-git-credential
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_path = "Ebrahimaabdelghfar/Ubuntu_assistant_Gemma2B"
torch.backends.cuda.enable_mem_efficient_sdp(False)
torch.backends.cuda.enable_flash_sdp(False)
tokenizer = AutoTokenizer.from_pretrained(model_path,max_new_tokens=1000000)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "what sudo do?"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'),max_length=1023,max_new_tokens=100)
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
print(response)
``` |