From 4164e2941692312ecc6f0edfeeaae16d7c409c61 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 25 Feb 2024 15:06:08 -0800 Subject: [PATCH 01/10] Block the "To create a public link, set share=True" gradio message --- modules/block_requests.py | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/modules/block_requests.py b/modules/block_requests.py index 38f1a17f..fbc45de4 100644 --- a/modules/block_requests.py +++ b/modules/block_requests.py @@ -7,6 +7,7 @@ from modules.logging_colors import logger original_open = open original_get = requests.get +original_print = print class RequestBlocker: @@ -22,9 +23,11 @@ class OpenMonkeyPatch: def __enter__(self): builtins.open = my_open + builtins.print = my_print def __exit__(self, exc_type, exc_value, traceback): builtins.open = original_open + builtins.print = original_print def my_get(url, **kwargs): @@ -45,3 +48,15 @@ def my_open(*args, **kwargs): return io.BytesIO(file_contents) else: return original_open(*args, **kwargs) + + +def my_print(*args, **kwargs): + if len(args) > 0 and 'To create a public link, set `share=True`' in args[0]: + return + else: + if len(args) > 0 and 'Running on local URL' in args[0]: + args = list(args) + args[0] = f"\n{args[0].strip()}\n" + args = tuple(args) + + original_print(*args, **kwargs) From 21acf504ce5e543541dbd2271215d69ea2967385 Mon Sep 17 00:00:00 2001 From: Bartowski Date: Sun, 25 Feb 2024 18:15:13 -0500 Subject: [PATCH 02/10] Bump transformers to 4.38 for gemma compatibility (#5575) --- requirements.txt | 2 +- requirements_amd.txt | 2 +- requirements_amd_noavx2.txt | 2 +- requirements_apple_intel.txt | 2 +- requirements_apple_silicon.txt | 2 +- requirements_cpu_only.txt | 2 +- requirements_cpu_only_noavx2.txt | 2 +- requirements_noavx2.txt | 2 +- requirements_nowheels.txt | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/requirements.txt b/requirements.txt index 8bf9f2f7..28982cb0 100644 --- a/requirements.txt +++ b/requirements.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_amd.txt b/requirements_amd.txt index 5353c2ef..6ad505ca 100644 --- a/requirements_amd.txt +++ b/requirements_amd.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt index a0373469..8b5b0a56 100644 --- a/requirements_amd_noavx2.txt +++ b/requirements_amd_noavx2.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt index 674df2d2..a6e454eb 100644 --- a/requirements_apple_intel.txt +++ b/requirements_apple_intel.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt index f6e00209..eef75554 100644 --- a/requirements_apple_silicon.txt +++ b/requirements_apple_silicon.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt index 97680f80..d67a361c 100644 --- a/requirements_cpu_only.txt +++ b/requirements_cpu_only.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt index 0e2276fd..dc67d87c 100644 --- a/requirements_cpu_only_noavx2.txt +++ b/requirements_cpu_only_noavx2.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt index 2f32aeba..c5f70fae 100644 --- a/requirements_noavx2.txt +++ b/requirements_noavx2.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt index c0827918..88580972 100644 --- a/requirements_nowheels.txt +++ b/requirements_nowheels.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers==4.37.* +transformers>=4.38.* tqdm wandb From 830168d3d44816d4e4ee743826a9f354db8ea8aa Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Mon, 26 Feb 2024 05:54:33 -0800 Subject: [PATCH 03/10] Revert "Replace hashlib.sha256 with hashlib.file_digest so we don't need to load entire files into ram before hashing them. (#4383)" This reverts commit 0ced78fdfa5a1747257f28183836a76b2bfde2a5. --- download-model.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/download-model.py b/download-model.py index d7cf9273..f4e1f607 100644 --- a/download-model.py +++ b/download-model.py @@ -262,7 +262,8 @@ class ModelDownloader: continue with open(output_folder / sha256[i][0], "rb") as f: - file_hash = hashlib.file_digest(f, "sha256").hexdigest() + bytes = f.read() + file_hash = hashlib.sha256(bytes).hexdigest() if file_hash != sha256[i][1]: print(f'Checksum failed: {sha256[i][0]} {sha256[i][1]}') validated = False From 332957ffec098e3f944e5bbd1cd2c06f6e595da0 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Mon, 26 Feb 2024 15:05:53 -0800 Subject: [PATCH 04/10] Bump llama-cpp-python to 0.2.52 --- requirements.txt | 24 ++++++++++++------------ requirements_amd.txt | 12 ++++++------ requirements_amd_noavx2.txt | 8 ++++---- requirements_apple_intel.txt | 12 ++++++------ requirements_apple_silicon.txt | 16 ++++++++-------- requirements_cpu_only.txt | 8 ++++---- requirements_cpu_only_noavx2.txt | 8 ++++---- requirements_noavx2.txt | 24 ++++++++++++------------ 8 files changed, 56 insertions(+), 56 deletions(-) diff --git a/requirements.txt b/requirements.txt index 28982cb0..413065dd 100644 --- a/requirements.txt +++ b/requirements.txt @@ -28,22 +28,22 @@ bitsandbytes==0.42.*; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" # llama-cpp-python (CPU only, AVX2) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" # llama-cpp-python (CUDA, no tensor cores) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" # llama-cpp-python (CUDA, tensor cores) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" # CUDA wheels https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" diff --git a/requirements_amd.txt b/requirements_amd.txt index 6ad505ca..6561412a 100644 --- a/requirements_amd.txt +++ b/requirements_amd.txt @@ -28,14 +28,14 @@ bitsandbytes==0.38.1; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows" # llama-cpp-python (CPU only, AVX2) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" # AMD wheels -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.50+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.50+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.52+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.52+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.14/exllamav2-0.0.14+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt index 8b5b0a56..73c3f1f2 100644 --- a/requirements_amd_noavx2.txt +++ b/requirements_amd_noavx2.txt @@ -28,10 +28,10 @@ bitsandbytes==0.38.1; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows" # llama-cpp-python (CPU only, no AVX2) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" # AMD wheels https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt index a6e454eb..b1b90a18 100644 --- a/requirements_apple_intel.txt +++ b/requirements_apple_intel.txt @@ -28,10 +28,10 @@ bitsandbytes==0.42.*; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" # Mac wheels -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.14/exllamav2-0.0.14-py3-none-any.whl diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt index eef75554..1f98776c 100644 --- a/requirements_apple_silicon.txt +++ b/requirements_apple_silicon.txt @@ -28,12 +28,12 @@ bitsandbytes==0.42.*; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" # Mac wheels -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.50-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.14/exllamav2-0.0.14-py3-none-any.whl diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt index d67a361c..5249397e 100644 --- a/requirements_cpu_only.txt +++ b/requirements_cpu_only.txt @@ -28,7 +28,7 @@ bitsandbytes==0.42.*; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" # llama-cpp-python (CPU only, AVX2) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt index dc67d87c..ee7b50f3 100644 --- a/requirements_cpu_only_noavx2.txt +++ b/requirements_cpu_only_noavx2.txt @@ -28,7 +28,7 @@ bitsandbytes==0.42.*; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" # llama-cpp-python (CPU only, no AVX2) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt index c5f70fae..9ee11e9a 100644 --- a/requirements_noavx2.txt +++ b/requirements_noavx2.txt @@ -28,22 +28,22 @@ bitsandbytes==0.42.*; platform_system != "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" # llama-cpp-python (CPU only, no AVX2) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.50+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" # llama-cpp-python (CUDA, no tensor cores) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.50+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.52+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" # llama-cpp-python (CUDA, tensor cores) -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.50+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.52+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" # CUDA wheels https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" From dfdf6eb5b41c5820a71705b262d152317732f027 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 26 Feb 2024 20:51:39 -0300 Subject: [PATCH 05/10] Bump hqq from 0.1.3 to 0.1.3.post1 (#5582) --- requirements.txt | 2 +- requirements_amd.txt | 2 +- requirements_amd_noavx2.txt | 2 +- requirements_apple_intel.txt | 2 +- requirements_apple_silicon.txt | 2 +- requirements_cpu_only.txt | 2 +- requirements_cpu_only_noavx2.txt | 2 +- requirements_noavx2.txt | 2 +- requirements_nowheels.txt | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/requirements.txt b/requirements.txt index 413065dd..226a0aeb 100644 --- a/requirements.txt +++ b/requirements.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_amd.txt b/requirements_amd.txt index 6561412a..2b11019e 100644 --- a/requirements_amd.txt +++ b/requirements_amd.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt index 73c3f1f2..dfc0a20a 100644 --- a/requirements_amd_noavx2.txt +++ b/requirements_amd_noavx2.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt index b1b90a18..8e9c56a8 100644 --- a/requirements_apple_intel.txt +++ b/requirements_apple_intel.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt index 1f98776c..e599bd9f 100644 --- a/requirements_apple_silicon.txt +++ b/requirements_apple_silicon.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt index 5249397e..9e60d2c8 100644 --- a/requirements_cpu_only.txt +++ b/requirements_cpu_only.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt index ee7b50f3..da4c3da3 100644 --- a/requirements_cpu_only_noavx2.txt +++ b/requirements_cpu_only_noavx2.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt index 9ee11e9a..c2449913 100644 --- a/requirements_noavx2.txt +++ b/requirements_noavx2.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt index 88580972..4b4429ef 100644 --- a/requirements_nowheels.txt +++ b/requirements_nowheels.txt @@ -3,7 +3,7 @@ colorama datasets einops gradio==3.50.* -hqq==0.1.3 +hqq==0.1.3.post1 jinja2==3.1.2 lm_eval==0.3.0 markdown From 09b13acfb25d3f0c46c52663977b6a6cb2b7cae2 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Wed, 28 Feb 2024 19:58:21 -0800 Subject: [PATCH 06/10] Perplexity evaluation: print to terminal after calculation is finished --- modules/evaluate.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/modules/evaluate.py b/modules/evaluate.py index b78c7b31..35c72689 100644 --- a/modules/evaluate.py +++ b/modules/evaluate.py @@ -127,9 +127,14 @@ def calculate_perplexity(models, input_dataset, stride, _max_length): break ppl = torch.exp(torch.stack(nlls).mean()) + add_entry_to_past_evaluations(float(ppl), shared.model_name, input_dataset, stride, _max_length) save_past_evaluations(past_evaluations) - cumulative_log += f"The perplexity for `{shared.model_name}` is: {float(ppl)}\n\n" + + message = f"The perplexity for `{shared.model_name}` is: {float(ppl)}" + logger.info(message) + + cumulative_log += f"{message}\n\n" yield cumulative_log From 3168644152cb473a1a5084202b05fd5acbd46d41 Mon Sep 17 00:00:00 2001 From: jeffbiocode <142954341+jeffbiocode@users.noreply.github.com> Date: Mon, 4 Mar 2024 00:42:14 +0900 Subject: [PATCH 07/10] Training: Update llama2-chat-format.json (#5593) --- training/formats/llama2-chat-format.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/training/formats/llama2-chat-format.json b/training/formats/llama2-chat-format.json index 8f8f4e6b..5d43c59b 100644 --- a/training/formats/llama2-chat-format.json +++ b/training/formats/llama2-chat-format.json @@ -1,4 +1,4 @@ { - "modelanswer,userprompt,systemprompt": "[INST] <>\n%systemprompt%\n<>\n\n%userprompt%[/INST] %modelanswer%" + "modelanswer,userprompt,systemprompt": "[INST] <>\n%systemprompt%\n<>\n\n%userprompt%[/INST] %modelanswer%", "modelanswer,userprompt": "[INST] <>\n\n<>\n\n%userprompt%[/INST] %modelanswer%" } From cfb25c9b3f0dc1521ff00036364b1235ef50e8e6 Mon Sep 17 00:00:00 2001 From: kalomaze <66376113+kalomaze@users.noreply.github.com> Date: Sun, 3 Mar 2024 10:22:21 -0600 Subject: [PATCH 08/10] Cubic sampling w/ curve param (#5551) --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com> --- extensions/openai/typing.py | 1 + modules/loaders.py | 3 +++ modules/presets.py | 3 ++- modules/sampler_hijack.py | 27 +++++++++++++++++---------- modules/text_generation.py | 2 +- modules/ui.py | 1 + modules/ui_parameters.py | 1 + 7 files changed, 26 insertions(+), 12 deletions(-) diff --git a/extensions/openai/typing.py b/extensions/openai/typing.py index ec351167..3ae02e68 100644 --- a/extensions/openai/typing.py +++ b/extensions/openai/typing.py @@ -13,6 +13,7 @@ class GenerationOptions(BaseModel): dynatemp_high: float = 1 dynatemp_exponent: float = 1 smoothing_factor: float = 0 + smoothing_curve: float = 1 top_k: int = 0 repetition_penalty: float = 1 repetition_penalty_range: int = 1024 diff --git a/modules/loaders.py b/modules/loaders.py index 08a7f229..513fd910 100644 --- a/modules/loaders.py +++ b/modules/loaders.py @@ -164,6 +164,7 @@ def transformers_samplers(): 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', + 'smoothing_curve', 'top_p', 'min_p', 'top_k', @@ -240,6 +241,7 @@ loaders_samplers = { 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', + 'smoothing_curve', 'top_p', 'min_p', 'top_k', @@ -298,6 +300,7 @@ loaders_samplers = { 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', + 'smoothing_curve', 'top_p', 'min_p', 'top_k', diff --git a/modules/presets.py b/modules/presets.py index d4fcc7d0..7a041311 100644 --- a/modules/presets.py +++ b/modules/presets.py @@ -19,6 +19,7 @@ def default_preset(): 'dynatemp_high': 1, 'dynatemp_exponent': 1, 'smoothing_factor': 0, + 'smoothing_curve': 1, 'top_p': 1, 'min_p': 0, 'top_k': 0, @@ -109,7 +110,7 @@ def random_preset(state): [1, 2], [1, 5] ], - 'smoothing_factor': [0.2, 0.3, 0.6, 1.2] + 'smoothing_factor': [0.2, 0.3, 0.6, 1.2], }, 'repetition': { 'repetition_penalty': [1, 1.05, 1.1, 1.15, 1.20, 1.25], diff --git a/modules/sampler_hijack.py b/modules/sampler_hijack.py index 057052e9..da52f4d0 100644 --- a/modules/sampler_hijack.py +++ b/modules/sampler_hijack.py @@ -99,22 +99,27 @@ class DynamicTemperatureLogitsWarper(LogitsWarper): class QuadraticSamplingLogitsWarper(LogitsWarper): ''' - Quadratic sampling. + Quadratic sampling with smoothing factor and smoothing curve parameters. ''' - def __init__(self, smoothing_factor: float): + def __init__(self, smoothing_factor, smoothing_curve): self.smoothing_factor = smoothing_factor + self.smoothing_curve = smoothing_curve def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor: - # Compute the maximum logit value + + # Compute necessary values max_logit = scores.max() + diff = scores - max_logit + k = (3 - self.smoothing_curve) / 2 + s = (self.smoothing_curve - 1) / 2 - # Apply the quadratic transformation - transformed_logits = -(self.smoothing_factor * (scores - max_logit)**2) + max_logit - - # No need to print the top 5 logits since this is not required - # print("Original top 5 logits: ", torch.topk(scores, 5)) - # print("New top 5 logits: ", torch.topk(transformed_logits, 5)) + # Apply transformation to non-negative infinity values + transformed_logits = torch.where( + scores != float('-inf'), + -(k * self.smoothing_factor * diff**2) + (s * self.smoothing_factor * diff**3) + max_logit, + scores + ) return transformed_logits @@ -367,7 +372,8 @@ def get_logits_warper_patch(self, generation_config): if generation_config.smoothing_factor > 0: warpers_to_add.append( QuadraticSamplingLogitsWarper( - smoothing_factor=generation_config.smoothing_factor + smoothing_factor=generation_config.smoothing_factor, + smoothing_curve=generation_config.smoothing_curve ) ) @@ -468,6 +474,7 @@ def generation_config_init_patch(self, **kwargs): self.dynatemp_high = kwargs.pop("dynatemp_high", 1) self.dynatemp_exponent = kwargs.pop("dynatemp_exponent", 1) self.smoothing_factor = kwargs.pop("smoothing_factor", 0.0) + self.smoothing_curve = kwargs.pop("smoothing_curve", 1.0) self.tfs = kwargs.pop("tfs", 1.0) self.top_a = kwargs.pop("top_a", 0.0) self.mirostat_mode = kwargs.pop("mirostat_mode", 0) diff --git a/modules/text_generation.py b/modules/text_generation.py index c62b9b01..227d1822 100644 --- a/modules/text_generation.py +++ b/modules/text_generation.py @@ -286,7 +286,7 @@ def get_reply_from_output_ids(output_ids, state=None, starting_from=0): def generate_reply_HF(question, original_question, seed, state, stopping_strings=None, is_chat=False): generate_params = {} - for k in ['max_new_tokens', 'temperature', 'temperature_last', 'dynamic_temperature', 'dynatemp_low', 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', 'top_p', 'min_p', 'top_k', 'repetition_penalty', 'presence_penalty', 'frequency_penalty', 'repetition_penalty_range', 'typical_p', 'tfs', 'top_a', 'guidance_scale', 'penalty_alpha', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'do_sample', 'encoder_repetition_penalty', 'no_repeat_ngram_size', 'min_length', 'num_beams', 'length_penalty', 'early_stopping']: + for k in ['max_new_tokens', 'temperature', 'temperature_last', 'dynamic_temperature', 'dynatemp_low', 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', 'smoothing_curve', 'top_p', 'min_p', 'top_k', 'repetition_penalty', 'presence_penalty', 'frequency_penalty', 'repetition_penalty_range', 'typical_p', 'tfs', 'top_a', 'guidance_scale', 'penalty_alpha', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'do_sample', 'encoder_repetition_penalty', 'no_repeat_ngram_size', 'min_length', 'num_beams', 'length_penalty', 'early_stopping']: if k in state: generate_params[k] = state[k] diff --git a/modules/ui.py b/modules/ui.py index bb5a3339..6249bb48 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -123,6 +123,7 @@ def list_interface_input_elements(): 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', + 'smoothing_curve', 'top_p', 'min_p', 'top_k', diff --git a/modules/ui_parameters.py b/modules/ui_parameters.py index 078590dc..7aebe672 100644 --- a/modules/ui_parameters.py +++ b/modules/ui_parameters.py @@ -50,6 +50,7 @@ def create_ui(default_preset): shared.gradio['mirostat_tau'] = gr.Slider(0, 10, step=0.01, value=generate_params['mirostat_tau'], label='mirostat_tau') shared.gradio['mirostat_eta'] = gr.Slider(0, 1, step=0.01, value=generate_params['mirostat_eta'], label='mirostat_eta') shared.gradio['smoothing_factor'] = gr.Slider(0.0, 10.0, value=generate_params['smoothing_factor'], step=0.01, label='smoothing_factor', info='Activates Quadratic Sampling.') + shared.gradio['smoothing_curve'] = gr.Slider(1.0, 10.0, value=generate_params['smoothing_curve'], step=0.01, label='smoothing_curve', info='Adjusts the dropoff curve of Quadratic Sampling.') shared.gradio['dynamic_temperature'] = gr.Checkbox(value=generate_params['dynamic_temperature'], label='dynamic_temperature') shared.gradio['dynatemp_low'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_low'], step=0.01, label='dynatemp_low', visible=generate_params['dynamic_temperature']) shared.gradio['dynatemp_high'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_high'], step=0.01, label='dynatemp_high', visible=generate_params['dynamic_temperature']) From 71b1617c1be0a7a0e4213f22fc2a3c995f90c4dc Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 3 Mar 2024 08:24:54 -0800 Subject: [PATCH 09/10] Remove bitsandbytes from incompatible requirements.txt files --- requirements_amd.txt | 4 ---- requirements_amd_noavx2.txt | 4 ---- requirements_apple_intel.txt | 4 ---- requirements_apple_silicon.txt | 4 ---- requirements_cpu_only.txt | 4 ---- requirements_cpu_only_noavx2.txt | 4 ---- requirements_nowheels.txt | 4 ---- 7 files changed, 28 deletions(-) diff --git a/requirements_amd.txt b/requirements_amd.txt index 2b11019e..daceb752 100644 --- a/requirements_amd.txt +++ b/requirements_amd.txt @@ -23,10 +23,6 @@ transformers>=4.38.* tqdm wandb -# bitsandbytes -bitsandbytes==0.38.1; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows" - # llama-cpp-python (CPU only, AVX2) https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt index dfc0a20a..17e8f010 100644 --- a/requirements_amd_noavx2.txt +++ b/requirements_amd_noavx2.txt @@ -23,10 +23,6 @@ transformers>=4.38.* tqdm wandb -# bitsandbytes -bitsandbytes==0.38.1; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows" - # llama-cpp-python (CPU only, no AVX2) https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt index 8e9c56a8..25fc97f0 100644 --- a/requirements_apple_intel.txt +++ b/requirements_apple_intel.txt @@ -23,10 +23,6 @@ transformers>=4.38.* tqdm wandb -# bitsandbytes -bitsandbytes==0.42.*; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" - # Mac wheels https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt index e599bd9f..d99105cd 100644 --- a/requirements_apple_silicon.txt +++ b/requirements_apple_silicon.txt @@ -23,10 +23,6 @@ transformers>=4.38.* tqdm wandb -# bitsandbytes -bitsandbytes==0.42.*; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" - # Mac wheels https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.52-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt index 9e60d2c8..818d9c49 100644 --- a/requirements_cpu_only.txt +++ b/requirements_cpu_only.txt @@ -23,10 +23,6 @@ transformers>=4.38.* tqdm wandb -# bitsandbytes -bitsandbytes==0.42.*; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" - # llama-cpp-python (CPU only, AVX2) https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt index da4c3da3..86a2fa99 100644 --- a/requirements_cpu_only_noavx2.txt +++ b/requirements_cpu_only_noavx2.txt @@ -23,10 +23,6 @@ transformers>=4.38.* tqdm wandb -# bitsandbytes -bitsandbytes==0.42.*; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" - # llama-cpp-python (CPU only, no AVX2) https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.52+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt index 4b4429ef..8569f262 100644 --- a/requirements_nowheels.txt +++ b/requirements_nowheels.txt @@ -22,7 +22,3 @@ tensorboard transformers>=4.38.* tqdm wandb - -# bitsandbytes -bitsandbytes==0.42.*; platform_system != "Windows" -https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" From 314e42fd98b1c842fb8393b333bfb1db4c53da11 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 3 Mar 2024 10:49:28 -0800 Subject: [PATCH 10/10] Fix transformers requirement --- requirements.txt | 2 +- requirements_amd.txt | 2 +- requirements_amd_noavx2.txt | 2 +- requirements_apple_intel.txt | 2 +- requirements_apple_silicon.txt | 2 +- requirements_cpu_only.txt | 2 +- requirements_cpu_only_noavx2.txt | 2 +- requirements_noavx2.txt | 2 +- requirements_nowheels.txt | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/requirements.txt b/requirements.txt index 226a0aeb..abbd1a62 100644 --- a/requirements.txt +++ b/requirements.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_amd.txt b/requirements_amd.txt index daceb752..56c1bb03 100644 --- a/requirements_amd.txt +++ b/requirements_amd.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt index 17e8f010..58b3fd1a 100644 --- a/requirements_amd_noavx2.txt +++ b/requirements_amd_noavx2.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt index 25fc97f0..cd9eaacb 100644 --- a/requirements_apple_intel.txt +++ b/requirements_apple_intel.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt index d99105cd..c0faebc0 100644 --- a/requirements_apple_silicon.txt +++ b/requirements_apple_silicon.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt index 818d9c49..19286bf1 100644 --- a/requirements_cpu_only.txt +++ b/requirements_cpu_only.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt index 86a2fa99..a71e4a7c 100644 --- a/requirements_cpu_only_noavx2.txt +++ b/requirements_cpu_only_noavx2.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt index c2449913..8244aa5f 100644 --- a/requirements_noavx2.txt +++ b/requirements_noavx2.txt @@ -19,7 +19,7 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt index 8569f262..4dc697a6 100644 --- a/requirements_nowheels.txt +++ b/requirements_nowheels.txt @@ -19,6 +19,6 @@ safetensors==0.4.* scipy sentencepiece tensorboard -transformers>=4.38.* +transformers==4.38.* tqdm wandb