AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add --text-only option to the download script

Browse Source
This commit is contained in:
oobabooga 2023-02-12 00:42:56 -03:00
parent 42cc307409
commit bf9dd8f8ee
2 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -105,14 +105,12 @@ After downloading the model, follow these steps:
1. Place the files under `models/gpt4chan_model_float16` or `models/gpt4chan_model`. 1. Place the files under `models/gpt4chan_model_float16` or `models/gpt4chan_model`.
2. Place GPT-J 6B's config.json file in that same folder: [config.json](https://huggingface.co/EleutherAI/gpt-j-6B/raw/main/config.json). 2. Place GPT-J 6B's config.json file in that same folder: [config.json](https://huggingface.co/EleutherAI/gpt-j-6B/raw/main/config.json).
3. Download GPT-J 6B under `models/gpt-j-6B`: 3. Download GPT-J 6B's tokenizer files (they will be automatically detected when you attempt to load GPT-4chan):
``` ```
python download-model.py EleutherAI/gpt-j-6B python download-model.py EleutherAI/gpt-j-6B --text-only
``` ```
You don't really need all of GPT-J 6B's files, just the tokenizer files, but you might as well download the whole thing. Those files will be automatically detected when you attempt to load GPT-4chan.
#### Converting to pytorch (optional) #### Converting to pytorch (optional)
The script `convert-to-torch.py` allows you to convert models to .pt format, which is sometimes 10x faster to load to the GPU: The script `convert-to-torch.py` allows you to convert models to .pt format, which is sometimes 10x faster to load to the GPU:

18
download-model.py
View File

@ -19,6 +19,7 @@ parser = argparse.ArgumentParser()
parser.add_argument('MODEL', type=str) parser.add_argument('MODEL', type=str)
parser.add_argument('--branch', type=str, default='main', help='Name of the Git branch to download from.') parser.add_argument('--branch', type=str, default='main', help='Name of the Git branch to download from.')
parser.add_argument('--threads', type=int, default=1, help='Number of files to download simultaneously.') parser.add_argument('--threads', type=int, default=1, help='Number of files to download simultaneously.')
parser.add_argument('--text-only', action='store_true', help='Only download text files (txt/json).')
args = parser.parse_args() args = parser.parse_args()
def get_file(args): def get_file(args):
@ -84,15 +85,18 @@ if __name__ == '__main__':
is_text = re.match(".*\.(txt|json)", fname) is_text = re.match(".*\.(txt|json)", fname)
if is_text or is_safetensors or is_pytorch: if is_text or is_safetensors or is_pytorch:
downloads.append(f'https://huggingface.co/{href}')
if is_text: if is_text:
downloads.append(f'https://huggingface.co/{href}')
classifications.append('text') classifications.append('text')
elif is_safetensors: continue
has_safetensors = True if not args.text_only:
classifications.append('safetensors') downloads.append(f'https://huggingface.co/{href}')
elif is_pytorch: if is_safetensors:
has_pytorch = True has_safetensors = True
classifications.append('pytorch') classifications.append('safetensors')
elif is_pytorch:
has_pytorch = True
classifications.append('pytorch')
# If both pytorch and safetensors are available, download safetensors only # If both pytorch and safetensors are available, download safetensors only
if has_pytorch and has_safetensors: if has_pytorch and has_safetensors: