v1.4.3 (#1609)

huggingface · Feb 28, 2024 · e6bb3ff · e6bb3ff
1 parent 26cdea5
commit e6bb3ff
Show file tree

Hide file tree

Showing 12 changed files with 86 additions and 88 deletions.
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/Cargo.toml b/Cargo.toml
@@ -9,7 +9,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "1.4.2"
+version = "1.4.3"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

diff --git a/docs/openapi.json b/docs/openapi.json
@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "1.4.2"
+    "version": "1.4.3"
   },
   "paths": {
     "/": {

diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml
@@ -9,8 +9,6 @@
     title: Supported Models and Hardware
   - local: messages_api
     title: Messages API
-  - local: guidance
-    title: Guidance
   title: Getting started
 - sections:
   - local: basic_tutorials/consuming_tgi

diff --git a/docs/source/conceptual/guidance.md b/docs/source/conceptual/guidance.md
@@ -262,7 +262,7 @@ curl localhost:3000/v1/chat/completions \
     ],
     "tool_choice": "get_current_weather"
 }'
-// {"id":"","object":"text_completion","created":1709051640,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.2-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":19,"total_tokens":176}}
+// {"id":"","object":"text_completion","created":1709051640,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":19,"total_tokens":176}}
 ```
 
 <details>
@@ -362,7 +362,7 @@ if __name__ == "__main__":
     import asyncio
     asyncio.run(main())
 
-# {"id":"","object":"text_completion","created":1709051942,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.2-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":20,"total_tokens":177}}
+# {"id":"","object":"text_completion","created":1709051942,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":20,"total_tokens":177}}
 
 ```
 

diff --git a/...ration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json b/...ration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json
@@ -17,7 +17,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.2-native",
+  "system_fingerprint": "1.4.3-native",
   "usage": {
     "completion_tokens": 100,
     "prompt_tokens": 60,

diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json
@@ -29,7 +29,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.2-native",
+  "system_fingerprint": "1.4.3-native",
   "usage": {
     "completion_tokens": 29,
     "prompt_tokens": 316,

diff --git a/...tion-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json b/...tion-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json
@@ -29,7 +29,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.2-native",
+  "system_fingerprint": "1.4.3-native",
   "usage": {
     "completion_tokens": 29,
     "prompt_tokens": 316,

diff --git a/...on-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json b/...on-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json
@@ -28,7 +28,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.2-native",
+  "system_fingerprint": "1.4.3-native",
   "usage": {
     "completion_tokens": 21,
     "prompt_tokens": 187,

diff --git a/...on-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json b/...on-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json
@@ -23,5 +23,5 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.2-native"
+  "system_fingerprint": "1.4.3-native"
 }
diff --git a/integration-tests/pyproject.toml b/integration-tests/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-integration-tests"
-version = "1.4.2"
+version = "1.4.3"
 description = "Text Generation Inference integration tests"
 authors = ["Nicolas Patry <[email protected]>"]
 

diff --git a/server/pyproject.toml b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "text-generation-server"
-version = "1.4.2"
+version = "1.4.3"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <[email protected]>"]