From a17787201082951ae39c3c10436be4c16346f16a Mon Sep 17 00:00:00 2001 From: BUAADreamer <1428195643@qq.com> Date: Fri, 26 Apr 2024 23:18:58 +0800 Subject: [PATCH 1/3] add llava_150k en/zh mllm sft data --- data/dataset_info.json | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/data/dataset_info.json b/data/dataset_info.json index d053be1d..18c4699a 100644 --- a/data/dataset_info.json +++ b/data/dataset_info.json @@ -73,6 +73,36 @@ "assistant_tag": "assistant" } }, + "llava_150k_en": { + "hf_hub_url": "BUAADreamer/llava-en-zh-300k", + "subset": "en", + "formatting": "sharegpt", + "columns": { + "messages": "messages", + "images": "images" + }, + "tags": { + "role_tag": "role", + "content_tag": "content", + "user_tag": "user", + "assistant_tag": "assistant" + } + }, + "llava_150k_zh": { + "hf_hub_url": "BUAADreamer/llava-en-zh-300k", + "subset": "zh", + "formatting": "sharegpt", + "columns": { + "messages": "messages", + "images": "images" + }, + "tags": { + "role_tag": "role", + "content_tag": "content", + "user_tag": "user", + "assistant_tag": "assistant" + } + }, "example": { "script_url": "example_dataset", "columns": { From c29b257007a8de9735ecaf52afffa80fdcee6a24 Mon Sep 17 00:00:00 2001 From: hoshi-hiyouga Date: Fri, 26 Apr 2024 23:34:34 +0800 Subject: [PATCH 2/3] Update dataset_info.json --- data/dataset_info.json | 62 +++++++++++++++++++++--------------------- 1 file changed, 31 insertions(+), 31 deletions(-) diff --git a/data/dataset_info.json b/data/dataset_info.json index 18c4699a..479eb95b 100644 --- a/data/dataset_info.json +++ b/data/dataset_info.json @@ -73,36 +73,6 @@ "assistant_tag": "assistant" } }, - "llava_150k_en": { - "hf_hub_url": "BUAADreamer/llava-en-zh-300k", - "subset": "en", - "formatting": "sharegpt", - "columns": { - "messages": "messages", - "images": "images" - }, - "tags": { - "role_tag": "role", - "content_tag": "content", - "user_tag": "user", - "assistant_tag": "assistant" - } - }, - "llava_150k_zh": { - "hf_hub_url": "BUAADreamer/llava-en-zh-300k", - "subset": "zh", - "formatting": "sharegpt", - "columns": { - "messages": "messages", - "images": "images" - }, - "tags": { - "role_tag": "role", - "content_tag": "content", - "user_tag": "user", - "assistant_tag": "assistant" - } - }, "example": { "script_url": "example_dataset", "columns": { @@ -280,6 +250,36 @@ "response": "text" } }, + "llava_150k_en": { + "hf_hub_url": "BUAADreamer/llava-en-zh-300k", + "subset": "en", + "formatting": "sharegpt", + "columns": { + "messages": "messages", + "images": "images" + }, + "tags": { + "role_tag": "role", + "content_tag": "content", + "user_tag": "user", + "assistant_tag": "assistant" + } + }, + "llava_150k_zh": { + "hf_hub_url": "BUAADreamer/llava-en-zh-300k", + "subset": "zh", + "formatting": "sharegpt", + "columns": { + "messages": "messages", + "images": "images" + }, + "tags": { + "role_tag": "role", + "content_tag": "content", + "user_tag": "user", + "assistant_tag": "assistant" + } + }, "oasst_de": { "hf_hub_url": "mayflowergmbh/oasst_de" }, @@ -459,4 +459,4 @@ }, "folder": "python" } -} \ No newline at end of file +} From 456ad61ac5dfa7f5e18e18a1ef1300ebe7c95078 Mon Sep 17 00:00:00 2001 From: hoshi-hiyouga Date: Fri, 26 Apr 2024 23:36:13 +0800 Subject: [PATCH 3/3] Update dataset_info.json