orca_mini_v3_13b / README.md
Pankaj Mathur
Create README.md
3f768b0
|
raw
history blame
3.7 kB
---
datasets:
- psmathur/orca_minis_uncensored_dataset
language:
- en
library_name: transformers
---
# orca_mini_v3_13b
A Llama2-13b model trained on Orca Style datasets.
**I am actively seeking sponsorship and partnership opportunities. If you're interested, please connect with me at www.linkedin.com/in/pankajam.**
## Evaluation
We evaluated orca_mini_v3_13b on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|||||
|:------:|:--------:|:-------:|:--------:|
|**Task**|**Metric**|**Value**|**Stderr**|
|*arc_challenge*|acc_norm|0.5717|0.0145|
|*hellaswag*|acc_norm|0.7966|0.0043|
|*mmlu*|acc_norm|0.5234|0.035|
|*truthfulqa_mc*|mc2|0.5029|0.0156|
|**Total Average**|-|**0.59865**||
## Example Usage
Here is the prompt format
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
I want to build the best Large Language Model, Give me detail step by step instructions on how to do it?
### Assistant:
```
Below shows a code example on how to use this model
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("psmathur/orca_mini_v3_13b", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("psmathur/orca_mini_v3_13b", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
system_prompt = "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
#generate text steps
instruction = "I want to build the best Large Language Model, Give me detail step by step instructions on how to do it?"
prompt = f"{system_prompt}### User: {instruction}\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=4096)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
#### Limitations & Biases:
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
Exercise caution and cross-check information when necessary.
### Citiation:
Please kindly cite using the following BibTeX:
```
@misc{orca_mini_v3_13b,
author = {Pankaj Mathur},
title = {orca_mini_v3_13b: An explain tuned Llama2-13b model},
year = {2023},
publisher = {GitHub, HuggingFace},
journal = {GitHub repository, HuggingFace repository},
howpublished = {\url{https://https://huggingface.co/psmathur/orca_mini_v3_13b},
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@software{touvron2023llama,
title={LLaMA: Open and Efficient Foundation Language Models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
```