llama-cpp-python 0.2.14__tar.gz → 0.2.16__tar.gz

llama_cpp_python-0.2.16/.git/FETCH_HEAD

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906		'b7e60b66f47950e385980a1329af9dfb14da6906' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.2.16/.git/HEAD

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906

{llama_cpp_python-0.2.14 → llama_cpp_python-0.2.16}/.git/config

@@ -9,7 +9,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX0JoYkh4YlZ0cmp6anh3ajNkZ3pBOEFZREFmTVZQWjFsOFZnMQ==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzJBc3h5aUVKQkZ1Q3M5bjVaWU1ZTk9za3hoSzh0VDFMeVdwRw==
 [submodule "vendor/llama.cpp"]
 	active = true
 	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.16/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 b7e60b66f47950e385980a1329af9dfb14da6906 runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615337 +0000	checkout: moving from master to refs/tags/v0.2.16

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+a75fa576abba9d37f463580c379e4bbf1e1ad03c

{llama_cpp_python-0.2.14 → llama_cpp_python-0.2.16}/.git/modules/vendor/llama.cpp/config

@@ -13,7 +13,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX0JoYkh4YlZ0cmp6anh3ajNkZ3pBOEFZREFmTVZQWjFsOFZnMQ==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzJBc3h5aUVKQkZ1Q3M5bjVaWU1ZTk9za3hoSzh0VDFMeVdwRw==
 [url "https://github.com/"]
 	insteadOf = git@github.com:
 	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+a75fa576abba9d37f463580c379e4bbf1e1ad03c a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	checkout: moving from master to a75fa576abba9d37f463580c379e4bbf1e1ad03c

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+a75fa576abba9d37f463580c379e4bbf1e1ad03c refs/remotes/origin/master

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+a75fa576abba9d37f463580c379e4bbf1e1ad03c

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1 @@
+a75fa576abba9d37f463580c379e4bbf1e1ad03c

llama_cpp_python-0.2.16/.git/objects/b7/e60b66f47950e385980a1329af9dfb14da6906

@@ -0,0 +1,4 @@
+x
��Q�0��)��miwKb�r��,JB����%���If�Қ�T�9>բ
+ܣ%F�(6`p!1��&YQ
+N��}3�M�.ƞ}3R����%�\�t$��&!
+����x,C�	:��.p��7��,�|Ik����h=�1 ����%�n�|���u1_1�FW

llama_cpp_python-0.2.16/.git/refs/tags/v0.2.16

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906

llama_cpp_python-0.2.16/.git/shallow

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906

{llama_cpp_python-0.2.14 → llama_cpp_python-0.2.16}/.github/workflows/build-and-release.yaml

@@ -33,6 +33,9 @@ jobs:
 
       - name: Build wheels
         run: python -m cibuildwheel --output-dir wheelhouse
+        env:
+          # disable repair
+          CIBW_REPAIR_WHEEL_COMMAND: ""
 
       - uses: actions/upload-artifact@v3
         with:

{llama_cpp_python-0.2.14 → llama_cpp_python-0.2.16}/CHANGELOG.md

@@ -7,9 +7,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.16]
+
+- Update llama.cpp to ggerganov/llama.cp@a75fa576abba9d37f463580c379e4bbf1e1ad03c
+- Add `set_seed` to `Llama` class by @abetlen in fd41ed3a908761d286102a019a34c2938a15118d
+- Fix server doc arguments by @kjunggithub in #892
+- Fix response_format handler in llava chat handler by @abetlen in b62c44983921197ed10a7d29dc4ba920e9979380
+- Fix default max_tokens, chat completion is now unlimited (to context length) and completion is 16 tokens to match OpenAI defaults by @abetlen in e7962d2c733cbbeec5a37392c81f64185a9a39e8
+- Fix json_schema_to_gbnf helper so that it takes a json schema string as input instead by @abetlen in faeae181b1e868643c0dc28fcf039f077baf0829
+- Add support for $ref and $def in json_schema_to_gbnf to handle more complex function schemas by @abetlen in 770df344369c0630df1be14be9f9e301e7c56d24
+- Update functionary chat handler for new OpenAI api by abetlen in 1b376c62b775b401653facf25a519d116aafe99a
+- Fix add default stop sequence to chatml chat format by @abetlen in b84d76a844149216d511cfd8cdb9827148a1853c
+- Fix sampling bug when logits_all=False by @abetlen in 6f0b0b1b840af846938ed74d0e8170a91c40e617
+
+## [0.2.15]
+
+- Update llama.cpp to ggerganov/llama.cpp@0a7c980b6f94a049cb804573df2d8092a34df8e4
+- Add support for Llava1.5 multimodal models by @damian0815 and @abetlen in #821
+- Update OpenAI API compatibility to match dev day update by @abetlen in #821
+- Add seed parameter to completion and chat_completion functions of Llama class by @abetlen in 86aeb9f3a14808575d2bb0076e6acb4a30907e6a
+- Add JSON mode support to constrain chat completion to JSON objects by @abetlen in b30b9c338bf9af316d497ea501d39f5c246900db
+
 ## [0.2.14]
 
-- Update llama.cpp to f0b30ef7dc1360922ccbea0a8cd3918ecf15eaa7
+- Update llama.cpp to ggerganov/llama.cpp@f0b30ef7dc1360922ccbea0a8cd3918ecf15eaa7
 - Add support for Huggingface Autotokenizer Chat Formats by @bioshazard and @abetlen in #790 and bbffdaebaa7bb04b543dbf683a07276087251f86
 - Fix llama-2 chat format by @earonesty in #869
 - Add support for functionary chat format by @abetlen in #784
@@ -17,7 +38,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.2.13]
 
-- Update llama.cpp to 51b2fc11f7f605fff49725a4540e9a6ef7b51b70
+- Update llama.cpp to ggerganov/llama.cpp@51b2fc11f7f605fff49725a4540e9a6ef7b51b70
 - Fix name 'open' is not defined exception when deleting model by @abetlen in 011b95d7f34cbfc528af75a892757bd9a20838ab
 - Fix tokenization of special characters by @antoine-lizee in #850
 

{llama_cpp_python-0.2.14 → llama_cpp_python-0.2.16}/CMakeLists.txt

@@ -41,4 +41,23 @@ if (LLAMA_BUILD)
         FILES $<TARGET_RUNTIME_DLLS:llama>
         DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
     )
+    add_subdirectory(vendor/llama.cpp/examples/llava)
+    set_target_properties(llava_shared PROPERTIES OUTPUT_NAME "llava")
+    install(
+        TARGETS llava_shared
+        LIBRARY DESTINATION ${SKBUILD_PLATLIB_DIR}/llama_cpp
+        RUNTIME DESTINATION ${SKBUILD_PLATLIB_DIR}/llama_cpp
+        ARCHIVE DESTINATION ${SKBUILD_PLATLIB_DIR}/llama_cpp
+        FRAMEWORK DESTINATION ${SKBUILD_PLATLIB_DIR}/llama_cpp
+        RESOURCE DESTINATION ${SKBUILD_PLATLIB_DIR}/llama_cpp
+    )
+    # Temporary fix for https://github.com/scikit-build/scikit-build-core/issues/374
+    install(
+        TARGETS llava_shared
+        LIBRARY DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
+        RUNTIME DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
+        ARCHIVE DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
+        FRAMEWORK DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
+        RESOURCE DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
+    )
 endif()

{llama_cpp_python-0.2.14 → llama_cpp_python-0.2.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama_cpp_python
-Version: 0.2.14
+Version: 0.2.16
 Summary: Python bindings for the llama.cpp library
 Author-Email: Andrei Betlen <abetlen@gmail.com>
 License: MIT

llama_cpp_python-0.2.16/docs/server.md

@@ -0,0 +1,121 @@
+# OpenAI Compatible Server
+
+`llama-cpp-python` offers an OpenAI API compatible web server.
+
+This web server can be used to serve local models and easily connect them to existing clients.
+
+## Setup
+
+### Installation
+
+The server can be installed by running the following command:
+
+```bash
+pip install llama-cpp-python[server]
+```
+
+### Running the server
+
+The server can then be started by running the following command:
+
+```bash
+python3 -m llama_cpp.server --model <model_path>
+```
+
+### Server options
+
+For a full list of options, run:
+
+```bash
+python3 -m llama_cpp.server --help
+```
+
+NOTE: All server options are also available as environment variables. For example, `--model` can be set by setting the `MODEL` environment variable.
+
+## Guides
+
+### Code Completion
+
+`llama-cpp-python` supports code completion via GitHub Copilot.
+
+*NOTE*: Without GPU acceleration this is unlikely to be fast enough to be usable.
+
+You'll first need to download one of the available code completion models in GGUF format:
+
+- [replit-code-v1_5-GGUF](https://huggingface.co/abetlen/replit-code-v1_5-3b-GGUF)
+
+Then you'll need to run the OpenAI compatible web server with a increased context size substantially for GitHub Copilot requests:
+
+```bash
+python3 -m llama_cpp.server --model <model_path> --n_ctx 16192
+```
+
+Then just update your settings in `.vscode/settings.json` to point to your code completion server:
+
+```json
+{
+    // ...
+    "github.copilot.advanced": {
+        "debug.testOverrideProxyUrl": "http://<host>:<port>",
+        "debug.overrideProxyUrl": "http://<host>:<port>"
+    }
+    // ...
+}
+```
+
+### Function Calling
+
+`llama-cpp-python` supports structured function calling based on a JSON schema.
+
+You'll first need to download one of the available function calling models in GGUF format:
+
+- [functionary-7b-v1](https://huggingface.co/abetlen/functionary-7b-v1-GGUF)
+
+Then when you run the server you'll need to also specify the `functionary-7b-v1` chat_format
+
+```bash
+python3 -m llama_cpp.server --model <model_path> --chat_format functionary
+```
+
+### Multimodal Models
+
+`llama-cpp-python` supports the llava1.5 family of multi-modal models which allow the language model to
+read information from both text and images.
+
+You'll first need to download one of the available multi-modal models in GGUF format:
+
+- [llava-v1.5-7b](https://huggingface.co/mys/ggml_llava-v1.5-7b)
+- [llava-v1.5-13b](https://huggingface.co/mys/ggml_llava-v1.5-13b)
+- [bakllava-1-7b](https://huggingface.co/mys/ggml_bakllava-1)
+
+Then when you run the server you'll need to also specify the path to the clip model used for image embedding and the `llava-1-5` chat_format
+
+```bash
+python3 -m llama_cpp.server --model <model_path> --clip_model_path <clip_model_path> --chat_format llava-1-5
+```
+
+Then you can just use the OpenAI API as normal
+
+```python3
+from openai import OpenAI
+
+client = OpenAI(base_url="http://<host>:<port>/v1", api_key="sk-xxx")
+response = client.chat.completions.create(
+    model="gpt-4-vision-preview",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": "<image_url>"
+                    },
+                },
+                {"type": "text", "text": "What does the image say"},
+            ],
+        }
+    ],
+)
+print(response)
+```