diff --git a/README.md b/README.md
index 952c07782a..f556b6a6e5 100644
--- a/README.md
+++ b/README.md
@@ -208,7 +208,7 @@ $ xinference registrations
 | LLM  | code-llama-python   | ['en']       | ['generate']           |
 | LLM  | falcon              | ['en']       | ['embed', 'generate']  |
 | LLM  | falcon-instruct     | ['en']       | ['embed', 'chat']      |
-| LLM  | glaive-coder        | ['en']       | ['chat']              |
+| LLM  | glaive-coder        | ['en']       | ['chat']               |
 | LLM  | gpt-2               | ['en']       | ['generate']           |
 | LLM  | internlm-7b         | ['en', 'zh'] | ['embed', 'generate']  |
 | LLM  | internlm-chat-7b    | ['en', 'zh'] | ['embed', 'chat']      |
@@ -217,6 +217,8 @@ $ xinference registrations
 | LLM  | llama-2-chat        | ['en']       | ['embed', 'chat']      |
 | LLM  | opt                 | ['en']       | ['embed', 'generate']  |
 | LLM  | orca                | ['en']       | ['embed', 'chat']      |
+| LLM  | phi1                | ['en']       | ['generate']           |
+| LLM  | phi1.5              | ['en']       | ['generate']           |
 | LLM  | qwen-chat           | ['en', 'zh'] | ['embed', 'chat']      |
 | LLM  | starchat-beta       | ['en']       | ['embed', 'chat']      |
 | LLM  | starcoder           | ['en']       | ['generate']           |
diff --git a/README_ja_JP.md b/README_ja_JP.md
index ed9b3ad336..4222c4f376 100644
--- a/README_ja_JP.md
+++ b/README_ja_JP.md
@@ -196,6 +196,8 @@ $ xinference registrations
 | LLM  | llama-2-chat        | ['en']       | ['embed', 'chat']     |
 | LLM  | opt                 | ['en']       | ['embed', 'generate'] |
 | LLM  | orca                | ['en']       | ['embed', 'chat']     |
+| LLM  | phi1                | ['en']       | ['generate']          |
+| LLM  | phi1.5              | ['en']       | ['generate']          |
 | LLM  | qwen-chat           | ['en', 'zh'] | ['embed', 'chat']     |
 | LLM  | starchat-beta       | ['en']       | ['embed', 'chat']     |
 | LLM  | starcoder           | ['en']       | ['generate']          |
diff --git a/README_zh_CN.md b/README_zh_CN.md
index 1dea7d9bd2..53531266ea 100644
--- a/README_zh_CN.md
+++ b/README_zh_CN.md
@@ -190,7 +190,7 @@ $ xinference registrations
 | LLM  | code-llama-python   | ['en']       | ['generate']           |
 | LLM  | falcon              | ['en']       | ['embed', 'generate']  |
 | LLM  | falcon-instruct     | ['en']       | ['embed', 'chat']      |
-| LLM  | glaive-coder        | ['en']       | ['chat']              |
+| LLM  | glaive-coder        | ['en']       | ['chat']               |
 | LLM  | gpt-2               | ['en']       | ['generate']           |
 | LLM  | internlm-7b         | ['en', 'zh'] | ['embed', 'generate']  |
 | LLM  | internlm-chat-7b    | ['en', 'zh'] | ['embed', 'chat']      |
@@ -199,6 +199,8 @@ $ xinference registrations
 | LLM  | llama-2-chat        | ['en']       | ['embed', 'chat']      |
 | LLM  | opt                 | ['en']       | ['embed', 'generate']  |
 | LLM  | orca                | ['en']       | ['embed', 'chat']      |
+| LLM  | phi1                | ['en']       | ['generate']           |
+| LLM  | phi1.5              | ['en']       | ['generate']           |
 | LLM  | qwen-chat           | ['en', 'zh'] | ['embed', 'chat']      |
 | LLM  | starchat-beta       | ['en']       | ['embed', 'chat']      |
 | LLM  | starcoder           | ['en']       | ['generate']           |
diff --git a/setup.cfg b/setup.cfg
index 74e2148c70..2d98c3ebff 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -65,7 +65,7 @@ dev =
 all =
     ctransformers
     llama-cpp-python>=0.2.0
-    transformers>=4.31.0
+    transformers>=4.34.0
     torch
     accelerate>=0.20.3
     sentencepiece
diff --git a/xinference/model/llm/llm_family.json b/xinference/model/llm/llm_family.json
index 957585f18c..f38b64b5f6 100644
--- a/xinference/model/llm/llm_family.json
+++ b/xinference/model/llm/llm_family.json
@@ -756,6 +756,56 @@
       }
     ]
   },
+  {
+    "version": 1,
+    "context_length": 2048,
+    "model_name": "phi-1",
+    "model_lang": [
+      "en"
+    ],
+    "model_ability": [
+      "generate"
+    ],
+    "model_description": "Phi-1 is a Transformer based LLM, trained on code and synthetic data for research on model safety.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 1,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "microsoft/phi-1",
+        "model_revision": "633bca15031ed2150e5badd538ec29d4e2403138"
+      }
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 2048,
+    "model_name": "phi-1_5",
+    "model_lang": [
+      "en"
+    ],
+    "model_ability": [
+      "generate"
+    ],
+    "model_description": "Phi-1.5 is a Transformer based LLM, trained on additional NLP synthetic texts for research on model safety.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 1,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "microsoft/phi-1_5",
+        "model_revision": "b6a7e2fe15c21f5847279f23e280cc5a0e7049ef"
+      }
+    ]
+  },
   {
     "version": 1,
     "context_length": 2048,