From 1b95913cadb0cb8291e7f82a7eae3561bb7819f8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 21 Jul 2026 14:46:07 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: MaziyarPanahi/Phi-4-mini-instruct-GGUF Source: Original Platform --- .gitattributes | 59 +++++++++++++++++++++++++++++++++ Phi-4-mini-instruct.Q2_K.gguf | 3 ++ Phi-4-mini-instruct.Q3_K_L.gguf | 3 ++ Phi-4-mini-instruct.Q3_K_M.gguf | 3 ++ Phi-4-mini-instruct.Q3_K_S.gguf | 3 ++ Phi-4-mini-instruct.Q4_K_M.gguf | 3 ++ Phi-4-mini-instruct.Q4_K_S.gguf | 3 ++ Phi-4-mini-instruct.Q5_K_M.gguf | 3 ++ Phi-4-mini-instruct.Q5_K_S.gguf | 3 ++ Phi-4-mini-instruct.Q6_K.gguf | 3 ++ Phi-4-mini-instruct.Q8_0.gguf | 3 ++ Phi-4-mini-instruct.fp16.gguf | 3 ++ README.md | 45 +++++++++++++++++++++++++ config.json | 3 ++ configuration.json | 1 + 15 files changed, 141 insertions(+) create mode 100644 .gitattributes create mode 100644 Phi-4-mini-instruct.Q2_K.gguf create mode 100644 Phi-4-mini-instruct.Q3_K_L.gguf create mode 100644 Phi-4-mini-instruct.Q3_K_M.gguf create mode 100644 Phi-4-mini-instruct.Q3_K_S.gguf create mode 100644 Phi-4-mini-instruct.Q4_K_M.gguf create mode 100644 Phi-4-mini-instruct.Q4_K_S.gguf create mode 100644 Phi-4-mini-instruct.Q5_K_M.gguf create mode 100644 Phi-4-mini-instruct.Q5_K_S.gguf create mode 100644 Phi-4-mini-instruct.Q6_K.gguf create mode 100644 Phi-4-mini-instruct.Q8_0.gguf create mode 100644 Phi-4-mini-instruct.fp16.gguf create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5ca29d6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Phi-4-mini-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Phi-4-mini-instruct.Q2_K.gguf b/Phi-4-mini-instruct.Q2_K.gguf new file mode 100644 index 0000000..4308e83 --- /dev/null +++ b/Phi-4-mini-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de544be3e9f6c9ed1a6fe95f27685d638a350efa068783eca13d5c207f5d3c0c +size 1682636096 diff --git a/Phi-4-mini-instruct.Q3_K_L.gguf b/Phi-4-mini-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e356470 --- /dev/null +++ b/Phi-4-mini-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33527a16190c2e662b37998043ed8bedcc58703384c7944732cc9f4d09491db +size 2249653568 diff --git a/Phi-4-mini-instruct.Q3_K_M.gguf b/Phi-4-mini-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0d14ebd --- /dev/null +++ b/Phi-4-mini-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:131973dea3be6b7d1b9c6e47f6fdf6c18251a20668e13c80bf42dd1f2fcbf346 +size 2117532992 diff --git a/Phi-4-mini-instruct.Q3_K_S.gguf b/Phi-4-mini-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..98be4c5 --- /dev/null +++ b/Phi-4-mini-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0479dcc09d7c4aac26a8e9ede30fc8b669acee4abd17ca8ca3da5076509c01d4 +size 1897332032 diff --git a/Phi-4-mini-instruct.Q4_K_M.gguf b/Phi-4-mini-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..33859a0 --- /dev/null +++ b/Phi-4-mini-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:855cf60f7f8108713fb0e739cab72fd9dbf6c6d4160bd7ff0358142c74ae3287 +size 2491874624 diff --git a/Phi-4-mini-instruct.Q4_K_S.gguf b/Phi-4-mini-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..39b1981 --- /dev/null +++ b/Phi-4-mini-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5482cf4a772b948d8852d0b4d8541c5a07557e6b68d980c388f3f92bfddbc389 +size 2337733952 diff --git a/Phi-4-mini-instruct.Q5_K_M.gguf b/Phi-4-mini-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8ea3025 --- /dev/null +++ b/Phi-4-mini-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247fa3c3949fb90240d9b46797181145f8a7e09760cdbb525c663b250ac26db5 +size 2848128320 diff --git a/Phi-4-mini-instruct.Q5_K_S.gguf b/Phi-4-mini-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..b2b9a22 --- /dev/null +++ b/Phi-4-mini-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b00c10eddb45d00d5ce93015d64b04b6b9e3fb8c6880e72e32c5fbb9d08f50 +size 2727804224 diff --git a/Phi-4-mini-instruct.Q6_K.gguf b/Phi-4-mini-instruct.Q6_K.gguf new file mode 100644 index 0000000..ebfd7d8 --- /dev/null +++ b/Phi-4-mini-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264ee581a593b13007d93cbb9bc8003f9c049edb7f757eed134c08e1bc8a87cf +size 3155623232 diff --git a/Phi-4-mini-instruct.Q8_0.gguf b/Phi-4-mini-instruct.Q8_0.gguf new file mode 100644 index 0000000..8aed4db --- /dev/null +++ b/Phi-4-mini-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56cccfeba1168a4fdd07197d8b5cdfb765eea720bdb4bad59211449687b82000 +size 4084611392 diff --git a/Phi-4-mini-instruct.fp16.gguf b/Phi-4-mini-instruct.fp16.gguf new file mode 100644 index 0000000..6796024 --- /dev/null +++ b/Phi-4-mini-instruct.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bb32183dad1cc57730edf523bd6ac18716005bb579384d279e029e63828f97 +size 7680694592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cbec4ce --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: microsoft/Phi-4-mini-instruct +inference: false +model_creator: microsoft +model_name: Phi-4-mini-instruct-GGUF +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +--- +# [MaziyarPanahi/Phi-4-mini-instruct-GGUF](https://huggingface.co/MaziyarPanahi/Phi-4-mini-instruct-GGUF) +- Model creator: [microsoft](https://huggingface.co/microsoft) +- Original model: [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) + +## Description +[MaziyarPanahi/Phi-4-mini-instruct-GGUF](https://huggingface.co/MaziyarPanahi/Phi-4-mini-instruct-GGUF) contains GGUF format model files for [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct). + +### About GGUF + +GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. + +Here is an incomplete list of clients and libraries that are known to support GGUF: + +* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. +* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. +* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. +* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. +* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. +* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. +* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. +* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. +* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. +* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. + +## Special thanks + +🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..9f0f76f --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "mistral" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file