commit bbd253ef2ec76a0e0d066936412c5a457d1629cf Author: ModelHub XC Date: Tue Apr 21 22:31:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/SmolLM2-1.7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7e47255 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5a31a1 --- /dev/null +++ b/README.md @@ -0,0 +1,46 @@ +--- +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +- text-generation +model_name: SmolLM2-1.7B-Instruct-GGUF +base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct +inference: false +model_creator: HuggingFaceTB +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +--- +# [MaziyarPanahi/SmolLM2-1.7B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM2-1.7B-Instruct-GGUF) +- Model creator: [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) +- Original model: [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) + +## Description +[MaziyarPanahi/SmolLM2-1.7B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM2-1.7B-Instruct-GGUF) contains GGUF format model files for [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-GGUF_imatrix.dat b/SmolLM2-1.7B-Instruct-GGUF_imatrix.dat new file mode 100644 index 0000000..c4e7bee --- /dev/null +++ b/SmolLM2-1.7B-Instruct-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0993c54dd7739a22033f0259a0ec65a5e35861c8aa3c30b5427a49182c703fc6 +size 1971626 diff --git a/SmolLM2-1.7B-Instruct.Q2_K.gguf b/SmolLM2-1.7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6e1c5b5 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8540bd01d96bfae7635d35e4fb443ec202d2da1104cbb13aeb5edfd5275c3d +size 674583456 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_L.gguf b/SmolLM2-1.7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6cd156f --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96c2fa02ce15ff8013567ec5e44756df89f922c2840872f2034a4df516b584a +size 932533152 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_M.gguf b/SmolLM2-1.7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..053820c --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288a6a081791fd3a5fa5c4402e3cdf7239d5d4515d69726555701d7628740cd7 +size 860181408 diff --git a/SmolLM2-1.7B-Instruct.Q4_K_M.gguf b/SmolLM2-1.7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..3df7ad5 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eed15c92fa16bbf543050ceee2a0b9c62107dadaee1bb44c8d6076584604caa +size 1055609760 diff --git a/SmolLM2-1.7B-Instruct.Q4_K_S.gguf b/SmolLM2-1.7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..592e911 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b59b1fa60253e53b848b18ab215e2a69df5c7ea3b13a6aabf77bec3ead405ad +size 999117728 diff --git a/SmolLM2-1.7B-Instruct.Q5_K_M.gguf b/SmolLM2-1.7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..b8fa53c --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc9d2a36d8dd6523960e6fc8b9767d44a8d1c071ccd3ca80f78a6efe0b156e4 +size 1225479072 diff --git a/SmolLM2-1.7B-Instruct.Q5_K_S.gguf b/SmolLM2-1.7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..c4bba56 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386ef06a9574c71c32cdcbd957289fadfdeaedde5790e3231d407226e6b85987 +size 1192055712 diff --git a/SmolLM2-1.7B-Instruct.Q6_K.gguf b/SmolLM2-1.7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..e0a589a --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6845b9b2e77aba91fa4d992ea379a8edecba046c3d818ed7d83c41465891f743 +size 1405965216 diff --git a/SmolLM2-1.7B-Instruct.Q8_0.gguf b/SmolLM2-1.7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..2025cdd --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd32a78f66154c8c8cb7aad393f30e087fc156fd20f3a42f40787953a42a62d +size 1820414880 diff --git a/SmolLM2-1.7B-Instruct.fp16.gguf b/SmolLM2-1.7B-Instruct.fp16.gguf new file mode 100644 index 0000000..02b7553 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3f0569a9d0b56d5d3b5b7944768c71bd2fef789f8b36b1b85a05d390850852 +size 3424735936 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