|
--- |
|
base_model: google/gemma-2-9b-it |
|
datasets: |
|
- nroggendorff/profession |
|
language: |
|
- en |
|
license: mit |
|
tags: |
|
- trl |
|
- sft |
|
- art |
|
- code |
|
- adam |
|
- gemma |
|
model-index: |
|
- name: pro |
|
results: [] |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# Profession LLM |
|
|
|
Pro is a language model fine-tuned on the [Profession dataset](https://huggingface.co/datasets/nroggendorff/profession) using Supervised Fine-Tuning (SFT) and Teacher Reinforced Learning (TRL) techniques. |
|
|
|
## Features |
|
|
|
- Utilizes SFT and TRL techniques for improved performance |
|
- Supports English language |
|
|
|
## Usage |
|
|
|
To use the LLM, you can load the model using the Hugging Face Transformers library: |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig |
|
import torch |
|
|
|
bnb_config = BitsAndBytesConfig( |
|
load_in_4bit=True, |
|
bnb_4bit_use_double_quant=True, |
|
bnb_4bit_quant_type="nf4", |
|
bnb_4bit_compute_dtype=torch.bfloat16 |
|
) |
|
|
|
model_id = "nroggendorff/gemma-pro" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config) |
|
|
|
prompt = "[INST] Write a poem about tomatoes in the style of Poe.[/INST]" |
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
|
|
outputs = model.generate(**inputs) |
|
|
|
generated_text = tokenizer.batch_decode(outputs)[0] |
|
print(generated_text) |
|
``` |
|
|
|
## License |
|
|
|
This project is licensed under the MIT License. |
