Skip to content

fix: tokenizer config should use local model path when possible #1518

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 1, 2024

Conversation

drbh
Copy link
Collaborator

@drbh drbh commented Feb 1, 2024

This PR fixes the issue with loading a local tokenizer config. Previously the default functionality would look in the current working directory. Now if a local model path is specified we will check that directory for the tokenizer_config.

Examples of valid commands

uses tokenizer_config from hub

text-generation-launcher --model-id HuggingFaceH4/zephyr-7b-beta

use tokenizer_config from local model path

text-generation-launcher \
  --model-id ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/

use specific tokenizer_config file

 text-generation-launcher \
  --model-id ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/ \
  --tokenizer-config-path ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/tokenizer_config.json


Co-authored-by: Nicolas Patry <[email protected]>
Copy link
Collaborator

@Narsil Narsil left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@drbh drbh merged commit ee1cf51 into main Feb 1, 2024
@drbh drbh deleted the tokenizer-config-prefer-local-model-path branch February 1, 2024 14:39
kdamaszk pushed a commit to kdamaszk/tgi-gaudi that referenced this pull request Apr 29, 2024
…ingface#1518)

This PR fixes the issue with loading a local tokenizer config.
Previously the default functionality would look in the current working
directory. Now if a local model path is specified we will check that
directory for the tokenizer_config.

## Examples of valid commands

uses tokenizer_config from hub
```
text-generation-launcher --model-id HuggingFaceH4/zephyr-7b-beta
```

use tokenizer_config from local model path
```
text-generation-launcher \
  --model-id ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/
```

use specific tokenizer_config file
```
 text-generation-launcher \
  --model-id ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/ \
  --tokenizer-config-path ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/tokenizer_config.json


```

---------

Co-authored-by: Nicolas Patry <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants