Skip to content
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.

Sign up for GitHub

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

Fix paths to AI Sweden Models reference and model loading #28423

Merged
merged 1 commit into from
Jan 15, 2024
Merged

Fix paths to AI Sweden Models reference and model loading #28423

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docs/source/en/model_doc/gpt-sw3.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,15 +30,15 @@ in collaboration with RISE and the WASP WARA for Media and Language. GPT-Sw3 has
320B tokens in Swedish, Norwegian, Danish, Icelandic, English, and programming code. The model was pretrained using a
causal language modeling (CLM) objective utilizing the NeMo Megatron GPT implementation.

This model was contributed by [AI Sweden](https://huggingface.co/AI-Sweden).
This model was contributed by [AI Sweden Models](https://huggingface.co/AI-Sweden-Models).

## Usage example

```python
>>> from transformers import AutoTokenizer, AutoModelForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("AI-Sweden/gpt-sw3-356m")
>>> model = AutoModelForCausalLM.from_pretrained("AI-Sweden/gpt-sw3-356m")
>>> tokenizer = AutoTokenizer.from_pretrained("AI-Sweden-Models/gpt-sw3-356m")
>>> model = AutoModelForCausalLM.from_pretrained("AI-Sweden-Models/gpt-sw3-356m")

>>> input_ids = tokenizer("Träd är fina för att", return_tensors="pt")["input_ids"]

Expand Down
26 changes: 15 additions & 11 deletions src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,20 +21,24 @@

PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"AI-Sweden/gpt-sw3-126m": "https://huggingface.co/AI-Sweden/gpt-sw3-126m/resolve/main/spiece.model",
"AI-Sweden/gpt-sw3-350m": "https://huggingface.co/AI-Sweden/gpt-sw3-350m/resolve/main/spiece.model",
"AI-Sweden/gpt-sw3-1.6b": "https://huggingface.co/AI-Sweden/gpt-sw3-1.6b/resolve/main/spiece.model",
"AI-Sweden/gpt-sw3-6.7b": "https://huggingface.co/AI-Sweden/gpt-sw3-6.7b/resolve/main/spiece.model",
"AI-Sweden/gpt-sw3-20b": "https://huggingface.co/AI-Sweden/gpt-sw3-20b/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-126m": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-356m": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-356m/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-1.3b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-6.7b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-6.7b-v2": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-20b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b/resolve/main/spiece.model",
"AI-Sweden-Models/gpt-sw3-40b": "https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b/resolve/main/spiece.model",
}
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"AI-Sweden/gpt-sw3-126m": 2048,
"AI-Sweden/gpt-sw3-350m": 2048,
"AI-Sweden/gpt-sw3-1.6b": 2048,
"AI-Sweden/gpt-sw3-6.7b": 2048,
"AI-Sweden/gpt-sw3-20b": 2048,
"AI-Sweden-Models/gpt-sw3-126m": 2048,
"AI-Sweden-Models/gpt-sw3-356m": 2048,
"AI-Sweden-Models/gpt-sw3-1.3b": 2048,
"AI-Sweden-Models/gpt-sw3-6.7b": 2048,
"AI-Sweden-Models/gpt-sw3-6.7b-v2": 2048,
"AI-Sweden-Models/gpt-sw3-20b": 2048,
"AI-Sweden-Models/gpt-sw3-40b": 2048,
}


Expand All @@ -49,7 +53,7 @@ class GPTSw3Tokenizer(PreTrainedTokenizer):
```python
>>> from transformers import GPTSw3Tokenizer

>>> tokenizer = GPTSw3Tokenizer.from_pretrained("AI-Sweden/gpt-sw3-126m")
>>> tokenizer = GPTSw3Tokenizer.from_pretrained("AI-Sweden-Models/gpt-sw3-126m")
>>> tokenizer("Svenska är kul!")["input_ids"]
[1814, 377, 3617, 63504]
```
Expand Down