From 573c09dc521f38d0dae3e66b13d64b3a59ac8538 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 8 Sep 2026 14:37:13 +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/calme-2.1-phi3-4b-GGUF Source: Original Platform --- .gitattributes | 59 +++++++++++++++++++++++++ Phi-3-mini-4k-instruct-v0.1.Q2_K.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q3_K_L.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q3_K_M.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q3_K_S.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q4_K_M.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q4_K_S.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q5_K_M.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q5_K_S.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q6_K.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.Q8_0.gguf | 3 ++ Phi-3-mini-4k-instruct-v0.1.fp16.gguf | 3 ++ README.md | 48 ++++++++++++++++++++ config.json | 3 ++ configuration.json | 1 + 15 files changed, 144 insertions(+) create mode 100644 .gitattributes create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q2_K.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q3_K_L.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q3_K_M.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q3_K_S.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q4_K_M.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q4_K_S.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q5_K_M.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q5_K_S.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q6_K.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.Q8_0.gguf create mode 100644 Phi-3-mini-4k-instruct-v0.1.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..7dc92f3 --- /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-3-mini-4k-instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.fp16.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Phi-3-mini-4k-instruct-v0.1.Q2_K.gguf b/Phi-3-mini-4k-instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..4b0f429 --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542da587f7bd31cd21a57cf849cef7ae0408e85ad40d65d624a19775457efa06 +size 1416203104 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q3_K_L.gguf b/Phi-3-mini-4k-instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..560198f --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1519fabccb3fdb3d67d36ee97355187893993ad0a6f90adc49bf91876aa95881 +size 2087596384 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q3_K_M.gguf b/Phi-3-mini-4k-instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..f70cc14 --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1318e0e3ac8ab74957a570443b85d4bb994fae6244e7850ad818dca822841c +size 1955475808 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q3_K_S.gguf b/Phi-3-mini-4k-instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..3420f22 --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf40333b4d08409acf240fc8a69d1de17f7579cec3add6c475bb465365dfa0b +size 1681797472 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q4_K_M.gguf b/Phi-3-mini-4k-instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..dd3124b --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec708e535b20a4a4b6b6fc3462e687fb82c9949a3c663e71a061e0671682547 +size 2393231200 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q4_K_S.gguf b/Phi-3-mini-4k-instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..1ca2130 --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e7a1a372d78c5473db91f226f0c85a656961bad8b8376f3a88ae09964235b5 +size 2188758880 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q5_K_M.gguf b/Phi-3-mini-4k-instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..8a70cfc --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6d1dcafcfe40f739ac923eccaf76bb2266460f9cf9cdae37ae923e747a86b4 +size 2815274848 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q5_K_S.gguf b/Phi-3-mini-4k-instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..4f27261 --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6345343eb38895fcb73734ae1223e6696f1ef9b1ae864a18cde38c99809e6baa +size 2641473376 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q6_K.gguf b/Phi-3-mini-4k-instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..7936d91 --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97e5873e632177d1ff9994227ae5f3af945ec9d97ff0f95c47e1752eaa1d0ad +size 3135851872 diff --git a/Phi-3-mini-4k-instruct-v0.1.Q8_0.gguf b/Phi-3-mini-4k-instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..be0af8c --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e53742d4433bc18c2be263c0723b06aabaf33ca398e816a9cc297dd6065f122 +size 4061221216 diff --git a/Phi-3-mini-4k-instruct-v0.1.fp16.gguf b/Phi-3-mini-4k-instruct-v0.1.fp16.gguf new file mode 100644 index 0000000..dfe32cd --- /dev/null +++ b/Phi-3-mini-4k-instruct-v0.1.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5922cef2c47a54bca8fd585b3d020d8ca2bb71f06117ef2baff5ccecb702ee +size 7643296096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..db06e71 --- /dev/null +++ b/README.md @@ -0,0 +1,48 @@ +--- +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +- phi +- phi-3 +- text-generation +model_name: calme-2.1-phi3-4b-GGUF +base_model: MaziyarPanahi/calme-2.1-phi3-4b +inference: false +model_creator: MaziyarPanahi +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +--- +# [MaziyarPanahi/calme-2.1-phi3-4b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.1-phi3-4b-GGUF) +- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi) +- Original model: [MaziyarPanahi/calme-2.1-phi3-4b](https://huggingface.co/MaziyarPanahi/calme-2.1-phi3-4b) + +## Description +[MaziyarPanahi/calme-2.1-phi3-4b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.1-phi3-4b-GGUF) contains GGUF format model files for [MaziyarPanahi/calme-2.1-phi3-4b](https://huggingface.co/MaziyarPanahi/calme-2.1-phi3-4b). + +### 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