|
--- |
|
license: cc-by-nc-4.0 |
|
--- |
|
|
|
JAX weights converted from Torch checkpoint at `facebook/galactica-6.7b`. |
|
|
|
```python |
|
(env) ubuntu@vm:~$ JAX_PLATFORM_NAME=cpu python3 |
|
>>> import jax |
|
>>> print(jax.devices()) |
|
[CpuDevice(id=0)] # Ensure that model weights are loaded into CPU RAM, not accelerator memory. |
|
>>> from transformers import FlaxOPTForCausalLM |
|
>>> model = FlaxOPTForCausalLM.from_pretrained("facebook/galactica-6.7b", from_pt=True) |
|
>>> model.push_to_hub(hf_model_repo) |
|
``` |
|
|
|
## Citation and Attribution |
|
|
|
Citation from the original repo is reproduced below as per the cc-by-nc-4.0 licsense. |
|
|
|
```bibtex |
|
@inproceedings{GALACTICA, |
|
title={GALACTICA: A Large Language Model for Science}, |
|
author={Ross Taylor and Marcin Kardas and Guillem Cucurull and Thomas Scialom and Anthony Hartshorn and Elvis Saravia and Andrew Poulton and Viktor Kerkez and Robert Stojnic}, |
|
year={2022} |
|
} |
|
``` |
|
|
|
> Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC) |
