---
base_model: Azrail/smallm_70
library_name: transformers
model_name: smallm_70_instruct
tags:
- generated_from_trainer
- trl
- sft
- smallm
licence: license
---

# Model Card for smallm_70_instruct

This model is a fine-tuned version of [Azrail/smallm_70](https://huggingface.co/Azrail/smallm_70).
It has been trained using [TRL](https://github.com/huggingface/trl).

## Quick start

```python
from transformers import pipeline, AutoTokenizer

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
tokenizer = AutoTokenizer.from_pretrained("Azrail/smallm_70_instruct")
generator = pipeline("text-generation", model="Azrail/smallm_70_instruct", device="cuda", trust_remote_code=True, tokenizer=tokenizer)
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/azrails-main/huggingface/runs/gjmja2rh) 


This model was trained with SFT.

### Framework versions

- TRL: 0.16.1
- Transformers: 4.50.3
- Pytorch: 2.6.0+cu126
- Datasets: 3.5.0
- Tokenizers: 0.21.1