From 850492dafaa8ef801a332d5a787cc9818c7b6072 Mon Sep 17 00:00:00 2001
From: zhuhao <37029601+hwzhuhao@users.noreply.github.com>
Date: Sat, 28 Sep 2024 21:40:27 +0800
Subject: [PATCH] feat: deprecate gte-Qwen2-7B-instruct embedding model (#8866)

---
 .../perfxcloud/llm/_position.yaml             | 21 +++++++++----------
 .../perfxcloud/text_embedding/_position.yaml  |  4 ++++
 .../text_embedding/gte-Qwen2-7B-instruct.yaml |  1 +
 3 files changed, 15 insertions(+), 11 deletions(-)
 create mode 100644 api/core/model_runtime/model_providers/perfxcloud/text_embedding/_position.yaml

diff --git a/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml b/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml
index 37bf400f1e..c6930e54f5 100644
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml
@@ -1,24 +1,23 @@
 - Qwen2.5-72B-Instruct
 - Qwen2.5-7B-Instruct
+- Qwen2-72B-Instruct
+- Qwen2-72B-Instruct-AWQ-int4
+- Qwen2-72B-Instruct-GPTQ-Int4
+- Qwen2-7B-Instruct
+- Qwen2-7B
+- Qwen1.5-110B-Chat-GPTQ-Int4
+- Qwen1.5-72B-Chat-GPTQ-Int4
+- Qwen1.5-7B
+- Qwen-14B-Chat-Int4
 - Yi-Coder-1.5B-Chat
 - Yi-Coder-9B-Chat
-- Qwen2-72B-Instruct-AWQ-int4
 - Yi-1_5-9B-Chat-16K
-- Qwen2-7B-Instruct
 - Reflection-Llama-3.1-70B
-- Qwen2-72B-Instruct
 - Meta-Llama-3.1-8B-Instruct
-
 - Meta-Llama-3.1-405B-Instruct-AWQ-INT4
 - Meta-Llama-3-70B-Instruct-GPTQ-Int4
-- chatglm3-6b
 - Meta-Llama-3-8B-Instruct
 - Llama3-Chinese_v2
 - deepseek-v2-lite-chat
-- Qwen2-72B-Instruct-GPTQ-Int4
-- Qwen2-7B
-- Qwen-14B-Chat-Int4
-- Qwen1.5-72B-Chat-GPTQ-Int4
-- Qwen1.5-7B
-- Qwen1.5-110B-Chat-GPTQ-Int4
 - deepseek-v2-chat
+- chatglm3-6b
diff --git a/api/core/model_runtime/model_providers/perfxcloud/text_embedding/_position.yaml b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/_position.yaml
new file mode 100644
index 0000000000..99163d4293
--- /dev/null
+++ b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/_position.yaml
@@ -0,0 +1,4 @@
+- gte-Qwen2-7B-instruct
+- BAAI/bge-large-en-v1.5
+- BAAI/bge-large-zh-v1.5
+- BAAI/bge-m3
diff --git a/api/core/model_runtime/model_providers/perfxcloud/text_embedding/gte-Qwen2-7B-instruct.yaml b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/gte-Qwen2-7B-instruct.yaml
index 03db0d8bce..161d5ea9a2 100644
--- a/api/core/model_runtime/model_providers/perfxcloud/text_embedding/gte-Qwen2-7B-instruct.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/text_embedding/gte-Qwen2-7B-instruct.yaml
@@ -2,3 +2,4 @@ model: gte-Qwen2-7B-instruct
 model_type: text-embedding
 model_properties:
   context_size: 2048
+deprecated: true