From 08bd0440b52dbe2e6d28323900ca1a07751605f9 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Mon, 27 May 2024 19:57:33 +0800
Subject: [PATCH] add llava 1k datasets

---
 README.md              |  2 +-
 README_zh.md           |  2 +-
 data/dataset_info.json | 30 ++++++++++++++++++++++++++++++
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 2b74bdb5..78312e07 100644
--- a/README.md
+++ b/README.md
@@ -107,7 +107,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 [24/02/05] Qwen1.5 (Qwen2 beta version) series models are supported in LLaMA-Factory. Check this [blog post](https://qwenlm.github.io/blog/qwen1.5/) for details.
 
-[24/01/18] We supported **agent tuning** for most models, equipping model with tool using abilities by fine-tuning with `dataset: glaive_toolcall`.
+[24/01/18] We supported **agent tuning** for most models, equipping model with tool using abilities by fine-tuning with `dataset: glaive_toolcall_en`.
 
 [23/12/23] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s implementation to boost LoRA tuning for the LLaMA, Mistral and Yi models. Try `use_unsloth: true` argument to activate unsloth patch. It achieves **170%** speed in our benchmark, check [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison) for details.
 
diff --git a/README_zh.md b/README_zh.md
index fa59a554..5acf3dd1 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -107,7 +107,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 [24/02/05] Qwen1.5（Qwen2 测试版）系列模型已在 LLaMA-Factory 中实现微调支持。详情请查阅该[博客页面](https://qwenlm.github.io/zh/blog/qwen1.5/)。
 
-[24/01/18] 我们针对绝大多数模型实现了 **Agent 微调**，微调时指定 `dataset: glaive_toolcall` 即可使模型获得工具调用能力。
+[24/01/18] 我们针对绝大多数模型实现了 **Agent 微调**，微调时指定 `dataset: glaive_toolcall_zh` 即可使模型获得工具调用能力。
 
 [23/12/23] 我们针对 LLaMA, Mistral 和 Yi 模型支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的 LoRA 训练加速。请使用 `use_unsloth: true` 参数启用 unsloth 优化。该方法可提供 **170%** 的训练速度，详情请查阅[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
 
diff --git a/data/dataset_info.json b/data/dataset_info.json
index b985582e..7420f3a8 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -248,6 +248,36 @@
   "ruozhiba_gpt4": {
     "hf_hub_url": "hfl/ruozhiba_gpt4_turbo"
   },
+  "llava_1k_en": {
+    "hf_hub_url": "BUAADreamer/llava-en-zh-2k",
+    "subset": "en",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "llava_1k_zh": {
+    "hf_hub_url": "BUAADreamer/llava-en-zh-2k",
+    "subset": "zh",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
   "llava_150k_en": {
     "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
     "subset": "en",