diff --git a/libs/model-providers/model_providers/core/model_runtime/model_providers/xinference/llm/_position.yaml b/libs/model-providers/model_providers/core/model_runtime/model_providers/xinference/llm/_position.yaml
deleted file mode 100644
index 36640c5e..00000000
--- a/libs/model-providers/model_providers/core/model_runtime/model_providers/xinference/llm/_position.yaml
+++ /dev/null
@@ -1 +0,0 @@
-- chatglm3-6b
diff --git a/libs/model-providers/model_providers/core/model_runtime/model_providers/xinference/llm/chatglm3-6b.yaml b/libs/model-providers/model_providers/core/model_runtime/model_providers/xinference/llm/chatglm3-6b.yaml
deleted file mode 100644
index 371b0126..00000000
--- a/libs/model-providers/model_providers/core/model_runtime/model_providers/xinference/llm/chatglm3-6b.yaml
+++ /dev/null
@@ -1,43 +0,0 @@
-model: chatglm3-6b
-label:
-  zh_Hans: chatglm3-6b
-  en_US: chatglm3-6b
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 4096
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 4096
-  - name: response_format
-    label:
-      zh_Hans: 回复格式
-      en_US: response_format
-    type: string
-    help:
-      zh_Hans: 指定模型必须输出的格式
-      en_US: specifying the format that the model must output
-    required: false
-    options:
-      - text
-      - json_object
-pricing:
-  input: '0.001'
-  output: '0.002'
-  unit: '0.001'
-  currency: USD
diff --git a/libs/model-providers/model_providers/core/provider_manager.py b/libs/model-providers/model_providers/core/provider_manager.py
index 1cde79d2..a4c2af32 100644
--- a/libs/model-providers/model_providers/core/provider_manager.py
+++ b/libs/model-providers/model_providers/core/provider_manager.py
@@ -239,7 +239,7 @@ class ProviderManager:
             if not provider_model_record.get("model_credentials"):
                 continue
 
-            provider_model_credentials = {}
+            provider_model_credentials = provider_model_record.get("model_credentials")
             for variable in model_credential_variables:
                 if variable in provider_model_record.get("model_credentials"):
                     try:
diff --git a/libs/model-providers/tests/unit_tests/xinference/model_providers.yaml b/libs/model-providers/tests/unit_tests/xinference/model_providers.yaml
index a7ee556d..f93d47e0 100644
--- a/libs/model-providers/tests/unit_tests/xinference/model_providers.yaml
+++ b/libs/model-providers/tests/unit_tests/xinference/model_providers.yaml
@@ -6,6 +6,7 @@ xinference:
       model_credentials:
         server_url: 'http://127.0.0.1:9997/'
         model_uid: 'chatglm3-6b'
+        completion_type: 'chat'
     - model: 'bge-m3'
       model_type: 'embeddings'
       completion_type: 'embeddings'