SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update all references to canonical models (#29001)

Browse Source 
* Script & Manual edition

* Update
This commit is contained in:
Lysandre Debut
2024-02-16 08:16:58 +01:00
committed by GitHub
parent 1e402b957d
commit f497f564bb
561 changed files with 2682 additions and 2687 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/research_projects/codeparrot/README.md
View File

@@ -79,7 +79,7 @@ python scripts/pretokenizing.py \
Before training a new model for code we create a new tokenizer that is efficient at code tokenization. To train the tokenizer you can run the following command:
```bash
python scripts/bpe_training.py \
--base_tokenizer gpt2 \
--base_tokenizer openai-community/gpt2 \
--dataset_name codeparrot/codeparrot-clean-train
```
@@ -90,12 +90,12 @@ The models are randomly initialized and trained from scratch. To initialize a ne
```bash
python scripts/initialize_model.py \
--config_name gpt2-large \
--config_name openai-community/gpt2-large \
--tokenizer_name codeparrot/codeparrot \
--model_name codeparrot \
--push_to_hub True
```
This will initialize a new model with the architecture and configuration of `gpt2-large` and use the tokenizer to appropriately size the input embeddings. Finally, the initilaized model is pushed the hub.
This will initialize a new model with the architecture and configuration of `openai-community/gpt2-large` and use the tokenizer to appropriately size the input embeddings. Finally, the initilaized model is pushed the hub.
We can either pass the name of a text dataset or a pretokenized dataset which speeds up training a bit.
Now that the tokenizer and model are also ready we can start training the model. The main training script is built with `accelerate` to scale across a wide range of platforms and infrastructure scales. We train two models with [110M](https://huggingface.co/codeparrot/codeparrot-small/) and [1.5B](https://huggingface.co/codeparrot/codeparrot/) parameters for 25-30B tokens on a 16xA100 (40GB) machine which takes 1 day and 1 week, respectively.

4
examples/research_projects/codeparrot/scripts/arguments.py
View File

@@ -172,7 +172,7 @@ class TokenizerTrainingArguments:
"""
base_tokenizer: Optional[str] = field(
default="gpt2", metadata={"help": "Base tokenizer to build new tokenizer from."}
default="openai-community/gpt2", metadata={"help": "Base tokenizer to build new tokenizer from."}
)
dataset_name: Optional[str] = field(
default="transformersbook/codeparrot-train", metadata={"help": "Dataset to train tokenizer on."}
@@ -211,7 +211,7 @@ class InitializationArguments:
"""
config_name: Optional[str] = field(
default="gpt2-large", metadata={"help": "Configuration to use for model initialization."}
default="openai-community/gpt2-large", metadata={"help": "Configuration to use for model initialization."}
)
tokenizer_name: Optional[str] = field(
default="codeparrot/codeparrot", metadata={"help": "Tokenizer attached to model."}