chore: bump lama-cpp-python to 0.2.79

umbertogriffo · Aug 16, 2024 · 4d5a733 · 4d5a733
1 parent 8110883
commit 4d5a733
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 6 deletions.
diff --git a/Makefile b/Makefile
@@ -16,7 +16,7 @@ install_cuda:
 	poetry config virtualenvs.in-project true
 	poetry install --extras "cuda-acceleration" --no-root --no-ansi
 	echo "Installing llama-cpp-python and ctransformers with pip to get NVIDIA CUDA acceleration"
-	. .venv/bin/activate && CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip3 install llama-cpp-python==$(llama_cpp_version)
+	. .venv/bin/activate && CMAKE_ARGS="-DGGML_CUDA=on" pip3 install llama-cpp-python==$(llama_cpp_version) -v
 	. .venv/bin/activate && pip3 install ctransformers[cuda]==$(ctransformers_version)
 
 install_metal:
@@ -25,7 +25,7 @@ install_metal:
 	poetry config virtualenvs.in-project true
 	poetry install --no-root --no-ansi
 	echo "Installing llama-cpp-python and ctransformers with pip to get Metal GPU acceleration for macOS systems only (it doesn't install CUDA dependencies)"
-	. .venv/bin/activate && CMAKE_ARGS="-DLLAMA_METAL" pip3 install llama-cpp-python==$(llama_cpp_version)
+	. .venv/bin/activate && CMAKE_ARGS="-DGGML_METAL=on" pip3 install llama-cpp-python==$(llama_cpp_version) -v
 	. .venv/bin/activate && CT_METAL=1 pip install ctransformers==$(ctransformers_version) --no-binary ctransformers
 
 install_pre_commit:

diff --git a/README.md b/README.md
@@ -137,9 +137,9 @@ format.
 
 | 🤖 Model                                   | Supported | Model Size | Notes and link to the model                                                                                                                                          |
 |--------------------------------------------|-----------|------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `llama-3` Meta Llama 3.1 Instruct          | ✅         | 8B         | [link](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF)                                                                                             |
+| `llama-3` Meta Llama 3.1 Instruct          | ✅         | 8B         | **Recommended model** [link](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF)                                                                       |
 | `openchat-3.6` - OpenChat 3.6              | ✅         | 8B         | [link](https://huggingface.co/bartowski/openchat-3.6-8b-20240522-GGUF)                                                                                               |
-| `openchat-3.5` - OpenChat 3.5              | ✅         | 7B         | **Recommended model** [link](https://huggingface.co/TheBloke/openchat-3.5-0106-GGUF)                                                                                 |
+| `openchat-3.5` - OpenChat 3.5              | ✅         | 7B         | [link](https://huggingface.co/TheBloke/openchat-3.5-0106-GGUF)                                                                                                       |
 | `starling` Starling Beta                   | ✅         | 7B         | Is trained from `Openchat-3.5-0106`. It's recommended if you prefer more verbosity over OpenChat - [link](https://huggingface.co/bartowski/Starling-LM-7B-beta-GGUF) |
 | `dolphin` Dolphin 2.6 Mistral DPO Laser    | ✅         | 7B         | [link](https://huggingface.co/TheBloke/dolphin-2.6-mistral-7B-dpo-laser-GGUF)                                                                                        |
 | `zephyr` Zephyr Beta                       | ✅         | 7B         | [link](https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF)                                                                                                          |

diff --git a/chatbot/helpers/log.py b/chatbot/helpers/log.py
@@ -6,9 +6,11 @@
 def get_logger(name: str):
     level = os.environ.get("LOGLEVEL", "INFO").upper()
     logger = logging.getLogger(name)
+
+    # Prevent double configuration by checking handlers
     if not logger.hasHandlers():
         logger.setLevel(level)
-
+        # Stream handler to stdout
         handler = logging.StreamHandler(sys.stdout)
         handler.setLevel(level)
         formatter = logging.Formatter("[%(thread)d] %(asctime)s - %(name)s - %(levelname)s - %(message)s")

diff --git a/version/llama_cpp b/version/llama_cpp
@@ -1 +1 @@
-0.2.76
+0.2.79