Update docs & Add EXAONE to SPECIAL_MODEL_NAME_LINK_MAPPING

huggingface · Nov 12, 2024 · d155f81 · d155f81
1 parent 12a9bfa
commit d155f81
Show file tree

Hide file tree

Showing 7 changed files with 14 additions and 10 deletions.
diff --git a/docs/source/en/_toctree.yml b/docs/source/en/_toctree.yml
@@ -390,8 +390,8 @@
         title: ErnieM
       - local: model_doc/esm
         title: ESM
-      - local: model_doc/exaone
-        title: EXAONE
+      - local: model_doc/exaone3
+        title: EXAONEv3.0
       - local: model_doc/falcon
         title: Falcon
       - local: model_doc/falcon_mamba

diff --git a/docs/source/en/index.md b/docs/source/en/index.md
@@ -135,7 +135,7 @@ Flax), PyTorch, and/or TensorFlow.
 |                         [ERNIE](model_doc/ernie)                         |       ✅        |         ❌         |      ❌      |
 |                       [ErnieM](model_doc/ernie_m)                        |       ✅        |         ❌         |      ❌      |
 |                           [ESM](model_doc/esm)                           |       ✅        |         ✅         |      ❌      |
-|                        [EXAONE](model_doc/exaone)                        |       ✅        |         ❌         |      ❌      |
+|                     [EXAONEv3.0](model_doc/exaone3)                      |       ✅        |         ❌         |      ❌      |
 |              [FairSeq Machine-Translation](model_doc/fsmt)               |       ✅        |         ❌         |      ❌      |
 |                        [Falcon](model_doc/falcon)                        |       ✅        |         ❌         |      ❌      |
 |                  [FalconMamba](model_doc/falcon_mamba)                   |       ✅        |         ❌         |      ❌      |

diff --git a/docs/source/en/model_doc/exaone.md → docs/source/en/model_doc/exaone3.md b/docs/source/en/model_doc/exaone.md → docs/source/en/model_doc/exaone3.md
@@ -1,4 +1,4 @@
-<!--Copyright 2024 The LG AI Research EXAONE Lab and The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The LG AI Research and The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -14,13 +14,15 @@ rendered properly in your Markdown viewer.
 
 -->
 
-# EXAONE
+# EXAONE v3.0
 
 _EXAONE stands for **EX**pert **A**I for Every**ONE**_
 
 ## Overview
-
-We introduce EXAONE-3.0-7.8B-Instruct, a pre-trained and instruction-tuned bilingual (English and Korean) generative model with 7.8 billion parameters. The model was pre-trained with 8T curated tokens and post-trained with supervised fine-tuning and direct preference optimization. It demonstrates highly competitive benchmark performance against other state-of-the-art open models of similar size.
+EXAONE is the family of Large Language Models (LLMs) and Large Multimodal Models (LMMs) developed by LG AI Research. EXAONE stands for EXpert AI for EveryONE, a vision that LG is committed to realizing.
+
+## Model Details
+`EXAONE-3.0-7.8B-Instruct` is a pre-trained and instruction-tuned bilingual (English and Korean) generative model with 7.8 billion parameters. The model was pre-trained with 8T curated tokens and post-trained with supervised fine-tuning and direct preference optimization. It demonstrates highly competitive benchmark performance against other state-of-the-art open models of similar size.
 
 ## Usage tips
 

diff --git a/docs/source/en/perf_infer_gpu_one.md b/docs/source/en/perf_infer_gpu_one.md
@@ -56,7 +56,7 @@ FlashAttention-2 is currently supported for the following architectures:
 * [GraniteMoe](https://huggingface.co/docs/transformers/model_doc/granitemoe#transformers.GraniteMoeModel)
 * [Idefics2](https://huggingface.co/docs/transformers/model_doc/idefics2#transformers.Idefics2Model)
 * [Idefics3](https://huggingface.co/docs/transformers/model_doc/idefics3#transformers.Idefics3Model)
-* [Exaone](https://huggingface.co/docs/transformers/model_doc/exaone#transformers.ExaoneModel)
+* [Exaone](https://huggingface.co/docs/transformers/model_doc/exaone3#transformers.ExaoneModel)
 * [Falcon](https://huggingface.co/docs/transformers/model_doc/falcon#transformers.FalconModel)
 * [JetMoe](https://huggingface.co/docs/transformers/model_doc/jetmoe#transformers.JetMoeModel)
 * [Jamba](https://huggingface.co/docs/transformers/model_doc/jamba#transformers.JambaModel)
@@ -232,7 +232,7 @@ For now, Transformers supports SDPA inference and training for the following arc
 * [DistilBert](https://huggingface.co/docs/transformers/model_doc/distilbert#transformers.DistilBertModel)
 * [Dpr](https://huggingface.co/docs/transformers/model_doc/dpr#transformers.DprReader)
 * [EncoderDecoder](https://huggingface.co/docs/transformers/model_doc/encoder_decoder#transformers.EncoderDecoderModel)
-* [Exaone](https://huggingface.co/docs/transformers/model_doc/exaone#transformers.ExaoneModel)
+* [Exaone](https://huggingface.co/docs/transformers/model_doc/exaone3#transformers.ExaoneModel)
 * [Falcon](https://huggingface.co/docs/transformers/model_doc/falcon#transformers.FalconModel)
 * [Gemma](https://huggingface.co/docs/transformers/model_doc/gemma#transformers.GemmaModel)
 * [Gemma2](https://huggingface.co/docs/transformers/model_doc/gemma2#transformers.Gemma2Model)

diff --git a/tests/models/exaone/test_modeling_exaone.py b/tests/models/exaone/test_modeling_exaone.py
@@ -1,5 +1,5 @@
 # coding=utf-8
-# Copyright 2024 The LG AI Research EXAONE Lab and The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The LG AI Research and The HuggingFace Inc. team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/utils/check_repo.py b/utils/check_repo.py
@@ -354,6 +354,7 @@
         ("data2vec-audio", "data2vec"),
         ("data2vec-vision", "data2vec"),
         ("donut-swin", "donut"),
+        ("exaone", "exaone3"),
     ]
 )
 

diff --git a/utils/check_table.py b/utils/check_table.py
@@ -138,6 +138,7 @@ def _center_text(text: str, width: int) -> str:
     "Data2VecText": "[Data2VecText](model_doc/data2vec)",
     "Data2VecVision": "[Data2VecVision](model_doc/data2vec)",
     "DonutSwin": "[DonutSwin](model_doc/donut)",
+    "EXAONE": "[EXAONEv3.0](model_doc/exaone3)",
 }
 
 MODEL_NAMES_WITH_SAME_CONFIG = {