From 4b1284b682debcf2079689987cea7716dd5c46d2 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 25 Jul 2026 18:38:06 +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/SmolLM-1.7B-Instruct-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++++++++++++ README.md | 45 ++++++++++++++++++++ SmolLM-1.7B-Instruct-GGUF_imatrix.dat | 3 ++ SmolLM-1.7B-Instruct.Q2_K.gguf | 3 ++ SmolLM-1.7B-Instruct.Q3_K_L.gguf | 3 ++ SmolLM-1.7B-Instruct.Q3_K_M.gguf | 3 ++ SmolLM-1.7B-Instruct.Q3_K_S.gguf | 3 ++ SmolLM-1.7B-Instruct.Q4_K_M.gguf | 3 ++ SmolLM-1.7B-Instruct.Q4_K_S.gguf | 3 ++ SmolLM-1.7B-Instruct.Q5_K_M.gguf | 3 ++ SmolLM-1.7B-Instruct.Q5_K_S.gguf | 3 ++ SmolLM-1.7B-Instruct.Q6_K.gguf | 3 ++ SmolLM-1.7B-Instruct.Q8_0.gguf | 3 ++ SmolLM-1.7B-Instruct.fp16.gguf | 3 ++ config.json | 3 ++ configuration.json | 1 + 16 files changed, 145 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 SmolLM-1.7B-Instruct-GGUF_imatrix.dat create mode 100644 SmolLM-1.7B-Instruct.Q2_K.gguf create mode 100644 SmolLM-1.7B-Instruct.Q3_K_L.gguf create mode 100644 SmolLM-1.7B-Instruct.Q3_K_M.gguf create mode 100644 SmolLM-1.7B-Instruct.Q3_K_S.gguf create mode 100644 SmolLM-1.7B-Instruct.Q4_K_M.gguf create mode 100644 SmolLM-1.7B-Instruct.Q4_K_S.gguf create mode 100644 SmolLM-1.7B-Instruct.Q5_K_M.gguf create mode 100644 SmolLM-1.7B-Instruct.Q5_K_S.gguf create mode 100644 SmolLM-1.7B-Instruct.Q6_K.gguf create mode 100644 SmolLM-1.7B-Instruct.Q8_0.gguf create mode 100644 SmolLM-1.7B-Instruct.fp16.gguf create mode 100644 config.json create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0c03a8e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 + +SmolLM-1.7B-Instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..655fa62 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: HuggingFaceTB/SmolLM-1.7B-Instruct +model_name: SmolLM-1.7B-Instruct-GGUF +pipeline_tag: text-generation +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +inference: false +model_creator: HuggingFaceTB +quantized_by: MaziyarPanahi +--- +# [MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF) +- Model creator: [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) +- Original model: [HuggingFaceTB/SmolLM-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct) + +## Description +[MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF) contains GGUF format model files for [HuggingFaceTB/SmolLM-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-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/SmolLM-1.7B-Instruct-GGUF_imatrix.dat b/SmolLM-1.7B-Instruct-GGUF_imatrix.dat new file mode 100644 index 0000000..6f7892f --- /dev/null +++ b/SmolLM-1.7B-Instruct-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3adfc5b49093db7fdb661be361f8a809a4302072649a49cb0125e66bbbc88d57 +size 1971626 diff --git a/SmolLM-1.7B-Instruct.Q2_K.gguf b/SmolLM-1.7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..08c6ed8 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26bb7914ecab259f979d8662dd2cc50528fd737471ba73bee6abdd58637ae632 +size 674583264 diff --git a/SmolLM-1.7B-Instruct.Q3_K_L.gguf b/SmolLM-1.7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e8f6154 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d452bad556495c12c2dea437ecc594d8ac381f97f6ffbd6dd78fe85c67e95cb +size 932532960 diff --git a/SmolLM-1.7B-Instruct.Q3_K_M.gguf b/SmolLM-1.7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0a1f9e7 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0c67d96ae556a6609b47432da1635776b9a96d6103b92b98dce28b46f8a490 +size 860181216 diff --git a/SmolLM-1.7B-Instruct.Q3_K_S.gguf b/SmolLM-1.7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..a6dc916 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49c1256b4b86cfc5bead61f1e54d01456f97646daee2f8155e4b6707d59fd3d +size 776819424 diff --git a/SmolLM-1.7B-Instruct.Q4_K_M.gguf b/SmolLM-1.7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..41ba28c --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b07eb2293ed3fc544a9858beda5bfb03dcabda6aa6582d3c85768c95f498d28 +size 1055609568 diff --git a/SmolLM-1.7B-Instruct.Q4_K_S.gguf b/SmolLM-1.7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..27b960a --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df76993e981498573ce2ef778c70c4e72bdb6831c501dcbee75c0cdc78445798 +size 999117536 diff --git a/SmolLM-1.7B-Instruct.Q5_K_M.gguf b/SmolLM-1.7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..20e642a --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f20f3c10a974cbca6e0a22df188d5b2e54b5a4bb3f9bd59167a4cd54cbaba16 +size 1225478880 diff --git a/SmolLM-1.7B-Instruct.Q5_K_S.gguf b/SmolLM-1.7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..7688944 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff11b8975f8ee251267ec2a2ebefd042d0d35109752359046118812ca8eb767 +size 1192055520 diff --git a/SmolLM-1.7B-Instruct.Q6_K.gguf b/SmolLM-1.7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..6020e31 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3cc5c33b39b9f66de068e1dcf3bfe0242caad597fa466746c99c5461679d0a +size 1405965024 diff --git a/SmolLM-1.7B-Instruct.Q8_0.gguf b/SmolLM-1.7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..0c51754 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c06fe58ce2d2c61f6927f17bde166d42a649781d75c92c0418236dec40a8c9 +size 1820414688 diff --git a/SmolLM-1.7B-Instruct.fp16.gguf b/SmolLM-1.7B-Instruct.fp16.gguf new file mode 100644 index 0000000..fe5cba9 --- /dev/null +++ b/SmolLM-1.7B-Instruct.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b093f5a62f9127e55e0c96046e14544ce34cd5d5ee56a0222fb0149e6fa8da59 +size 3424735744 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