From d0e99562af43a1bb33f7e7a4d4f3861407a2241f Mon Sep 17 00:00:00 2001 From: Gianluca Boiano <491117+M0Rf30@users.noreply.github.com> Date: Sun, 14 Sep 2025 15:04:58 +0200 Subject: [PATCH] chore(aio): upgrade minicpm-v model to latest 4.5 (#6262) chore(aio): upgrade vision model to MiniCPM-V 4.5 Signed-off-by: Gianluca Boiano --- aio/cpu/vision.yaml | 16 ++++++++-------- aio/gpu-8g/vision.yaml | 16 ++++++++-------- aio/intel/vision.yaml | 16 ++++++++-------- docs/content/docs/getting-started/quickstart.md | 2 +- 4 files changed, 25 insertions(+), 25 deletions(-) diff --git a/aio/cpu/vision.yaml b/aio/cpu/vision.yaml index fa31c2343..37852da05 100644 --- a/aio/cpu/vision.yaml +++ b/aio/cpu/vision.yaml @@ -2,10 +2,10 @@ context_size: 4096 f16: true backend: llama-cpp mmap: true -mmproj: minicpm-v-2_6-mmproj-f16.gguf +mmproj: minicpm-v-4_5-mmproj-f16.gguf name: gpt-4o parameters: - model: minicpm-v-2_6-Q4_K_M.gguf + model: minicpm-v-4_5-Q4_K_M.gguf stopwords: - <|im_end|> - @@ -42,9 +42,9 @@ template: <|im_start|>assistant download_files: -- filename: minicpm-v-2_6-Q4_K_M.gguf - sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1 - uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf -- filename: minicpm-v-2_6-mmproj-f16.gguf - uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf - sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd \ No newline at end of file +- filename: minicpm-v-4_5-Q4_K_M.gguf + sha256: c1c3c33100b15b4caf7319acce4e23c0eb0ce1cbd12f70e8d24f05aa67b7512f + uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/ggml-model-Q4_K_M.gguf +- filename: minicpm-v-4_5-mmproj-f16.gguf + uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/mmproj-model-f16.gguf + sha256: 7a7225a32e8d453aaa3d22d8c579b5bf833c253f784cdb05c99c9a76fd616df8 \ No newline at end of file diff --git a/aio/gpu-8g/vision.yaml b/aio/gpu-8g/vision.yaml index d1ef207fc..5c2d9930c 100644 --- a/aio/gpu-8g/vision.yaml +++ b/aio/gpu-8g/vision.yaml @@ -2,10 +2,10 @@ context_size: 4096 backend: llama-cpp f16: true mmap: true -mmproj: minicpm-v-2_6-mmproj-f16.gguf +mmproj: minicpm-v-4_5-mmproj-f16.gguf name: gpt-4o parameters: - model: minicpm-v-2_6-Q4_K_M.gguf + model: minicpm-v-4_5-Q4_K_M.gguf stopwords: - <|im_end|> - @@ -42,9 +42,9 @@ template: <|im_start|>assistant download_files: -- filename: minicpm-v-2_6-Q4_K_M.gguf - sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1 - uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf -- filename: minicpm-v-2_6-mmproj-f16.gguf - uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf - sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd \ No newline at end of file +- filename: minicpm-v-4_5-Q4_K_M.gguf + sha256: c1c3c33100b15b4caf7319acce4e23c0eb0ce1cbd12f70e8d24f05aa67b7512f + uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/ggml-model-Q4_K_M.gguf +- filename: minicpm-v-4_5-mmproj-f16.gguf + uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/mmproj-model-f16.gguf + sha256: 7a7225a32e8d453aaa3d22d8c579b5bf833c253f784cdb05c99c9a76fd616df8 \ No newline at end of file diff --git a/aio/intel/vision.yaml b/aio/intel/vision.yaml index 66cbd38dd..00b8c0680 100644 --- a/aio/intel/vision.yaml +++ b/aio/intel/vision.yaml @@ -2,10 +2,10 @@ context_size: 4096 backend: llama-cpp f16: true mmap: true -mmproj: minicpm-v-2_6-mmproj-f16.gguf +mmproj: minicpm-v-4_5-mmproj-f16.gguf name: gpt-4o parameters: - model: minicpm-v-2_6-Q4_K_M.gguf + model: minicpm-v-4_5-Q4_K_M.gguf stopwords: - <|im_end|> - @@ -43,9 +43,9 @@ template: download_files: -- filename: minicpm-v-2_6-Q4_K_M.gguf - sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1 - uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf -- filename: minicpm-v-2_6-mmproj-f16.gguf - uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf - sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd \ No newline at end of file +- filename: minicpm-v-4_5-Q4_K_M.gguf + sha256: c1c3c33100b15b4caf7319acce4e23c0eb0ce1cbd12f70e8d24f05aa67b7512f + uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/ggml-model-Q4_K_M.gguf +- filename: minicpm-v-4_5-mmproj-f16.gguf + uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/mmproj-model-f16.gguf + sha256: 7a7225a32e8d453aaa3d22d8c579b5bf833c253f784cdb05c99c9a76fd616df8 \ No newline at end of file diff --git a/docs/content/docs/getting-started/quickstart.md b/docs/content/docs/getting-started/quickstart.md index d9eb5227d..23b428805 100644 --- a/docs/content/docs/getting-started/quickstart.md +++ b/docs/content/docs/getting-started/quickstart.md @@ -182,7 +182,7 @@ MODEL_NAME=gemma-3-12b-it docker compose up # NVIDIA GPU setup with custom multimodal and image models MODEL_NAME=gemma-3-12b-it \ -MULTIMODAL_MODEL=minicpm-v-2_6 \ +MULTIMODAL_MODEL=minicpm-v-4_5 \ IMAGE_MODEL=flux.1-dev-ggml \ docker compose -f docker-compose.nvidia.yaml up ```