From 06c315bcb347ce65d29cf767958804e6fd7ed05f Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sun, 14 Jul 2024 23:14:34 +0200 Subject: [PATCH] models(gallery): add phi-3.1-mini-4k-instruct (#2863) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 42518cbd..535726ad 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3071,6 +3071,22 @@ - filename: phi3-4x4b-v1-Q4_K_M.gguf uri: huggingface://bartowski/phi3-4x4b-v1-GGUF/phi3-4x4b-v1-Q4_K_M.gguf sha256: fd33220186b7076f4b306f27b3a8913384435a2ca90185a71c9df5a752d3a298 +- !!merge <<: *phi-3 + name: "phi-3.1-mini-4k-instruct" + urls: + - https://huggingface.co/microsoft/Phi-3-mini-4k-instruct + - https://huggingface.co/bartowski/Phi-3.1-mini-4k-instruct-GGUF + description: | + This is an update over the original instruction-tuned Phi-3-mini release based on valuable customer feedback. The model used additional post-training data leading to substantial gains on instruction following and structure output. + + It is based on the original model from Microsoft, but has been updated and quantized using the llama.cpp release b3278. + overrides: + parameters: + model: Phi-3.1-mini-4k-instruct-Q4_K_M.gguf + files: + - filename: Phi-3.1-mini-4k-instruct-Q4_K_M.gguf + sha256: 39458b227a4be763b7eb39d306d240c3d45205e3f8b474ec7bdca7bba0158e69 + uri: huggingface://bartowski/Phi-3.1-mini-4k-instruct-GGUF/Phi-3.1-mini-4k-instruct-Q4_K_M.gguf - &hermes-2-pro-mistral ### START Hermes url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"