Merge branch 'master' into feat-request-middleware

mudler · Oct 16, 2024 · ed7f03e · ed7f03e
2 parents 0776abe + a60b9b7
commit ed7f03e
Show file tree

Hide file tree

Showing 19 changed files with 70 additions and 18 deletions.
diff --git a/Makefile b/Makefile
@@ -8,7 +8,7 @@ DETECT_LIBS?=true
 # llama.cpp versions
 GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
 GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=755a9b2bf00fbae988e03a47e852b66eaddd113a
+CPPLLAMA_VERSION?=9e041024481f6b249ab8918e18b9477f873b5a5e
 
 # go-rwkv version
 RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp

diff --git a/backend/python/autogptq/requirements.txt b/backend/python/autogptq/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 auto-gptq==0.7.1
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
 transformers
diff --git a/backend/python/bark/requirements.txt b/backend/python/bark/requirements.txt
@@ -1,4 +1,4 @@
 bark==0.1.5
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
diff --git a/backend/python/common/template/requirements.txt b/backend/python/common/template/requirements.txt
@@ -1,2 +1,2 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
diff --git a/backend/python/coqui/requirements.txt b/backend/python/coqui/requirements.txt
@@ -1,4 +1,4 @@
 coqui-tts
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
diff --git a/backend/python/diffusers/requirements.txt b/backend/python/diffusers/requirements.txt
@@ -1,5 +1,5 @@
 setuptools
-grpcio==1.66.2
+grpcio==1.67.0
 pillow
 protobuf
 certifi
diff --git a/backend/python/exllama2/requirements.txt b/backend/python/exllama2/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
 wheel

diff --git a/backend/python/mamba/requirements.txt b/backend/python/mamba/requirements.txt
@@ -1,3 +1,3 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
diff --git a/backend/python/openvoice/requirements-intel.txt b/backend/python/openvoice/requirements-intel.txt
@@ -2,7 +2,7 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 librosa==0.9.1
 faster-whisper==1.0.3

diff --git a/backend/python/openvoice/requirements.txt b/backend/python/openvoice/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 librosa
 faster-whisper

diff --git a/backend/python/parler-tts/requirements.txt b/backend/python/parler-tts/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
 llvmlite==0.43.0
diff --git a/backend/python/rerankers/requirements.txt b/backend/python/rerankers/requirements.txt
@@ -1,3 +1,3 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
diff --git a/backend/python/sentencetransformers/requirements.txt b/backend/python/sentencetransformers/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
 datasets

diff --git a/backend/python/transformers-musicgen/requirements.txt b/backend/python/transformers-musicgen/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 scipy==1.14.0
 certifi
diff --git a/backend/python/transformers/requirements.txt b/backend/python/transformers/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
 setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
diff --git a/backend/python/vall-e-x/requirements.txt b/backend/python/vall-e-x/requirements.txt
@@ -1,3 +1,3 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
diff --git a/backend/python/vllm/install.sh b/backend/python/vllm/install.sh
@@ -22,7 +22,7 @@ if [ "x${BUILD_TYPE}" == "x" ] && [ "x${FROM_SOURCE}" == "xtrue" ]; then
             git clone https://github.com/vllm-project/vllm
         fi
         pushd vllm
-            uv pip install wheel packaging ninja "setuptools>=49.4.0" numpy typing-extensions pillow setuptools-scm grpcio==1.66.2 protobuf bitsandbytes
+            uv pip install wheel packaging ninja "setuptools>=49.4.0" numpy typing-extensions pillow setuptools-scm grpcio==1.67.0 protobuf bitsandbytes
             uv pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
             VLLM_TARGET_DEVICE=cpu python setup.py install
         popd

diff --git a/backend/python/vllm/requirements.txt b/backend/python/vllm/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.66.2
+grpcio==1.67.0
 protobuf
 certifi
 setuptools
diff --git a/gallery/index.yaml b/gallery/index.yaml
@@ -572,6 +572,26 @@
     - filename: EdgeRunner-Command-Nested.i1-Q4_K_M.gguf
       sha256: a1cc4d2b601dc20e58cbb549bd3e9bc460995840c0aaf1cd3c1cb5414c900ac7
       uri: huggingface://mradermacher/EdgeRunner-Command-Nested-i1-GGUF/EdgeRunner-Command-Nested.i1-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "tsunami-0.5x-7b-instruct-i1"
+  icon: https://huggingface.co/Tsunami-th/Tsunami-0.5x-7B-Instruct/resolve/main/Tsunami.webp
+  urls:
+    - https://huggingface.co/Tsunami-th/Tsunami-0.5x-7B-Instruct
+    - https://huggingface.co/mradermacher/Tsunami-0.5x-7B-Instruct-i1-GGUF
+  description: |
+    TSUNAMI: Transformative Semantic Understanding and Natural Augmentation Model for Intelligence.
+
+    TSUNAMI full name was created by ChatGPT.
+    infomation
+
+    Tsunami-0.5x-7B-Instruct is Thai Large Language Model that fine-tuned from Qwen2.5-7B around 100,000 rows in Thai dataset.
+  overrides:
+    parameters:
+      model: Tsunami-0.5x-7B-Instruct.i1-Q4_K_M.gguf
+  files:
+    - filename: Tsunami-0.5x-7B-Instruct.i1-Q4_K_M.gguf
+      sha256: 22e2003ecec7f1e91f2e9aaec334613c0f37fb3000d0e628b5a9980e53322fa7
+      uri: huggingface://mradermacher/Tsunami-0.5x-7B-Instruct-i1-GGUF/Tsunami-0.5x-7B-Instruct.i1-Q4_K_M.gguf
 - &archfunct
   license: apache-2.0
   tags:
@@ -1620,6 +1640,38 @@
     - filename: Doctoraifinetune-3.1-8B.i1-Q4_K_M.gguf
       sha256: 282456efcb6c7e54d34ac25ae7fc022a94152ed77281ae4625b9628091e0a3d6
       uri: huggingface://mradermacher/Doctoraifinetune-3.1-8B-i1-GGUF/Doctoraifinetune-3.1-8B.i1-Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "astral-fusion-neural-happy-l3.1-8b"
+  urls:
+    - https://huggingface.co/ZeroXClem/Astral-Fusion-Neural-Happy-L3.1-8B
+    - https://huggingface.co/mradermacher/Astral-Fusion-Neural-Happy-L3.1-8B-GGUF
+  description: |
+    Astral-Fusion-Neural-Happy-L3.1-8B is a celestial blend of magic, creativity, and dynamic storytelling. Designed to excel in instruction-following, immersive roleplaying, and magical narrative generation, this model is a fusion of the finest qualities from Astral-Fusion, NIHAPPY, and NeuralMahou. ✨🚀
+
+    This model is perfect for anyone seeking a cosmic narrative experience, with the ability to generate both precise instructional content and fantastical stories in one cohesive framework. Whether you're crafting immersive stories, creating AI roleplaying characters, or working on interactive storytelling, this model brings out the magic. 🌟
+  overrides:
+    parameters:
+      model: Astral-Fusion-Neural-Happy-L3.1-8B.Q4_K_M.gguf
+  files:
+    - filename: Astral-Fusion-Neural-Happy-L3.1-8B.Q4_K_M.gguf
+      sha256: 14a3b07c1723ef1ca24f99382254b1227d95974541e23792a4e7ff621896055d
+      uri: huggingface://mradermacher/Astral-Fusion-Neural-Happy-L3.1-8B-GGUF/Astral-Fusion-Neural-Happy-L3.1-8B.Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "mahou-1.5-llama3.1-70b-i1"
+  url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
+  icon: https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png
+  urls:
+    - https://huggingface.co/flammenai/Mahou-1.5-llama3.1-70B
+    - https://huggingface.co/mradermacher/Mahou-1.5-llama3.1-70B-i1-GGUF
+  description: |
+    Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.
+  overrides:
+    parameters:
+      model: Mahou-1.5-llama3.1-70B.i1-Q4_K_M.gguf
+  files:
+    - filename: Mahou-1.5-llama3.1-70B.i1-Q4_K_M.gguf
+      sha256: c2711c4c9c8d011edbeaa391b4418d433e273a318d1de3dbdda9b85baf4996f2
+      uri: huggingface://mradermacher/Mahou-1.5-llama3.1-70B-i1-GGUF/Mahou-1.5-llama3.1-70B.i1-Q4_K_M.gguf
 - &deepseek
   ## Deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"