commit 21d96e5f6851aed769644a82460c0e7dbaea35e3 Author: ModelHub XC Date: Thu Sep 17 02:14:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/Vikhr-YandexGPT-5-Lite-8B-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6ecb916 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.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 +Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-YandexGPT-5-Lite-8B-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-YandexGPT-5-Lite-8B-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-YandexGPT-5-Lite-8B-it.fp16.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-YandexGPT-5-Lite-8B-it-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..894e5b6 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it +inference: false +model_creator: Vikhrmodels +model_name: Vikhr-YandexGPT-5-Lite-8B-it-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/Vikhr-YandexGPT-5-Lite-8B-it-GGUF](https://huggingface.co/MaziyarPanahi/Vikhr-YandexGPT-5-Lite-8B-it-GGUF) +- Model creator: [Vikhrmodels](https://huggingface.co/Vikhrmodels) +- Original model: [Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it](https://huggingface.co/Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it) + +## Description +[MaziyarPanahi/Vikhr-YandexGPT-5-Lite-8B-it-GGUF](https://huggingface.co/MaziyarPanahi/Vikhr-YandexGPT-5-Lite-8B-it-GGUF) contains GGUF format model files for [Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it](https://huggingface.co/Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it). + +### 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/Vikhr-YandexGPT-5-Lite-8B-it-GGUF_imatrix.dat b/Vikhr-YandexGPT-5-Lite-8B-it-GGUF_imatrix.dat new file mode 100644 index 0000000..16165aa --- /dev/null +++ b/Vikhr-YandexGPT-5-Lite-8B-it-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1927a12a1e53873a9aed97ce371319b0a680532fc15e807e7af64e71b5de5dd0 +size 4988146 diff --git a/Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_M.gguf b/Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_M.gguf new file mode 100644 index 0000000..2b4be89 --- /dev/null +++ b/Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e097ddd5d05fa1eaa292cc4d057746f3ce3cddd96d85a0eb0040fcd237039ebc +size 5733387744 diff --git a/Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_S.gguf b/Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_S.gguf new file mode 100644 index 0000000..41195fb --- /dev/null +++ b/Vikhr-YandexGPT-5-Lite-8B-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d381567579e7a18563bafde1b5c085136deffa07a1c86ae962f7161beac86358 +size 5599694304 diff --git a/Vikhr-YandexGPT-5-Lite-8B-it.Q6_K.gguf b/Vikhr-YandexGPT-5-Lite-8B-it.Q6_K.gguf new file mode 100644 index 0000000..9e4868c --- /dev/null +++ b/Vikhr-YandexGPT-5-Lite-8B-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8674095a01e4da52e5671788d031639b084ccbe9aa25cb92acb86ee8a574ed +size 6596824544 diff --git a/Vikhr-YandexGPT-5-Lite-8B-it.Q8_0.gguf b/Vikhr-YandexGPT-5-Lite-8B-it.Q8_0.gguf new file mode 100644 index 0000000..ccd66e7 --- /dev/null +++ b/Vikhr-YandexGPT-5-Lite-8B-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339361cd0f79b895c3248f784f4b9a225c739b74b74c93c357d1d578de169185 +size 8543112672 diff --git a/Vikhr-YandexGPT-5-Lite-8B-it.fp16.gguf b/Vikhr-YandexGPT-5-Lite-8B-it.fp16.gguf new file mode 100644 index 0000000..0d7c35f --- /dev/null +++ b/Vikhr-YandexGPT-5-Lite-8B-it.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e48b3762dbfade7fb91f588db490e00f439f6225f21d5b527187c40a32ee790 +size 16077130976 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