From 194064fdae0226dd22522586c9d47c5866a71a8e Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Mon, 2 Sep 2024 01:02:25 +0800
Subject: [PATCH] add pokemon dataset

---
 README.md              | 1 +
 README_zh.md           | 1 +
 data/dataset_info.json | 8 ++++++++
 3 files changed, 10 insertions(+)

diff --git a/README.md b/README.md
index eca3d1a1..e0ccb8e0 100644
--- a/README.md
+++ b/README.md
@@ -275,6 +275,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
 - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
+- [Pokemon-gpt4o-captions](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
 - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
 - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)
diff --git a/README_zh.md b/README_zh.md
index 256ebd1d..94a004ec 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -276,6 +276,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
 - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
+- [Pokemon-gpt4o-captions](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
 - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
 - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index 02597150..e95599c6 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -340,6 +340,14 @@
       "assistant_tag": "assistant"
     }
   },
+  "pokemon_cap": {
+    "hf_hub_url": "llamafactory/pokemon-gpt4o-captions",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "images": "images"
+    }
+  },
   "mllm_pt_demo": {
     "hf_hub_url": "BUAADreamer/mllm_pt_demo",
     "formatting": "sharegpt",