commit cd17824bf1bfa1ff207bb63cccc0d6865f26ad87 Author: ModelHub XC Date: Thu Apr 30 10:53:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/SmolLM2-1.7B-Instruct-16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..933da4f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.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 + +SmolLM2-1.7B-Instruct-16k.fp16.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-16k-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-16k.Q5_K_M.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..c102865 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct-16k +inference: false +model_creator: HuggingFaceTB +model_name: SmolLM2-1.7B-Instruct-16k-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/SmolLM2-1.7B-Instruct-16k-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM2-1.7B-Instruct-16k-GGUF) +- Model creator: [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) +- Original model: [HuggingFaceTB/SmolLM2-1.7B-Instruct-16k](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-16k) + +## Description +[MaziyarPanahi/SmolLM2-1.7B-Instruct-16k-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM2-1.7B-Instruct-16k-GGUF) contains GGUF format model files for [HuggingFaceTB/SmolLM2-1.7B-Instruct-16k](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-16k). + +### 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-16k-GGUF_imatrix.dat b/SmolLM2-1.7B-Instruct-16k-GGUF_imatrix.dat new file mode 100644 index 0000000..9d5e2ba --- /dev/null +++ b/SmolLM2-1.7B-Instruct-16k-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1c5e7bf192d622327e3a3be8bb2eb6155f1e4576915362519d399765fe383d +size 1971626 diff --git a/SmolLM2-1.7B-Instruct-16k.Q5_K_M.gguf b/SmolLM2-1.7B-Instruct-16k.Q5_K_M.gguf new file mode 100644 index 0000000..b739681 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b6d1e8440064b6022eafbc2497daba6bf26c1e47ee84227bcf75aa5ce95dfa +size 1225479296 diff --git a/SmolLM2-1.7B-Instruct-16k.Q5_K_S.gguf b/SmolLM2-1.7B-Instruct-16k.Q5_K_S.gguf new file mode 100644 index 0000000..ecc13c2 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2928013f8090264cde173e5eeffd9ce5e0ef5422a168d1b4f0b56608ff80d20 +size 1192055936 diff --git a/SmolLM2-1.7B-Instruct-16k.Q6_K.gguf b/SmolLM2-1.7B-Instruct-16k.Q6_K.gguf new file mode 100644 index 0000000..f006771 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86e118e73fa5931d8d82523ceec762a58ee9b40f6a61f766b8c0a5605331383a +size 1405965440 diff --git a/SmolLM2-1.7B-Instruct-16k.Q8_0.gguf b/SmolLM2-1.7B-Instruct-16k.Q8_0.gguf new file mode 100644 index 0000000..650da5b --- /dev/null +++ b/SmolLM2-1.7B-Instruct-16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58b8e7e1c469d00f5e69f3e4f1a7772b34e9d56b9ab51601e3c8f1ee274853a +size 1820415104 diff --git a/SmolLM2-1.7B-Instruct-16k.fp16.gguf b/SmolLM2-1.7B-Instruct-16k.fp16.gguf new file mode 100644 index 0000000..2aba8e2 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-16k.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cf76ce5d7b53ba8a9f48a8e1173e838203662418ee80cd353c283fbc0e8155 +size 3424736160 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