---
tags:
- autotrain
- text-generation-inference
- text-generation
- peft
library_name: transformers
base_model: Arthur-LAGACHERIE/Gemma-2-2b-4bit
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?
license: other
---


# Usage

This model uses the 4-bits quantization. So you need to install bitsandbytes to use it.
```python
pip install bitsandbytes
```
For inference (streaming):
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch
from transformers import TextIteratorStreamer
from threading import Thread
device = 'cuda' if torch.cuda.is_available() else 'cpu'

model_id = "Arthur-LAGACHERIE/Reflection-Gemma-2-2b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = """
### System
You are a world-class AI system, capable of complex reasoning and reflection. 
Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. 
If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
Try an answer and see if it's correct before generate the ouput. 
But don't forget to think very carefully.

### Question
The question here.
"""

chat = [
    { "role": "user", "content": prompt},
]
question = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
question = tokenizer(question, return_tensors="pt").to(device)
streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
generation_kwargs = dict(question, streamer=streamer, max_new_tokens=4000)
thread = Thread(target=model.generate, kwargs=generation_kwargs)

# generate
thread.start()
for new_text in streamer:
    print(new_text, end="")
```

# Some info
If you want to know how I fine tune it, what datasets I used and the training code. [See here]()



# Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).