commit 76b04ad31ed58d2325f274a6710d1383f8d9c07a Author: ModelHub XC Date: Sat Sep 12 23:36:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/granite-3.0-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..39a6f15 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.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 + +granite-3.0-8b-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-8b-instruct.Q3_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..3b53a40 --- /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: granite-3.0-8b-instruct-GGUF +base_model: ibm-granite/granite-3.0-8b-instruct +inference: false +model_creator: ibm-granite +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +--- +# [MaziyarPanahi/granite-3.0-8b-instruct-GGUF](https://huggingface.co/MaziyarPanahi/granite-3.0-8b-instruct-GGUF) +- Model creator: [ibm-granite](https://huggingface.co/ibm-granite) +- Original model: [ibm-granite/granite-3.0-8b-instruct](https://huggingface.co/ibm-granite/granite-3.0-8b-instruct) + +## Description +[MaziyarPanahi/granite-3.0-8b-instruct-GGUF](https://huggingface.co/MaziyarPanahi/granite-3.0-8b-instruct-GGUF) contains GGUF format model files for [ibm-granite/granite-3.0-8b-instruct](https://huggingface.co/ibm-granite/granite-3.0-8b-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/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 diff --git a/granite-3.0-8b-instruct-GGUF_imatrix.dat b/granite-3.0-8b-instruct-GGUF_imatrix.dat new file mode 100644 index 0000000..f51e9df --- /dev/null +++ b/granite-3.0-8b-instruct-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c5538370ff9a31d7b6705384bb72721131497c7614044347301babb07068b6 +size 5989434 diff --git a/granite-3.0-8b-instruct.IQ1_M.gguf b/granite-3.0-8b-instruct.IQ1_M.gguf new file mode 100644 index 0000000..f63f2bb --- /dev/null +++ b/granite-3.0-8b-instruct.IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed5d4a56eb9618619756f45b7e73ca58a6eb9e1dd5d07d4bccd364959a15d59 +size 1997503104 diff --git a/granite-3.0-8b-instruct.IQ1_S.gguf b/granite-3.0-8b-instruct.IQ1_S.gguf new file mode 100644 index 0000000..048a800 --- /dev/null +++ b/granite-3.0-8b-instruct.IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f31ac0a22228e81201b174be0e2d30936338f27c19a05a7a60e6b9e72cde282 +size 1836530304 diff --git a/granite-3.0-8b-instruct.IQ2_XS.gguf b/granite-3.0-8b-instruct.IQ2_XS.gguf new file mode 100644 index 0000000..cd99d0d --- /dev/null +++ b/granite-3.0-8b-instruct.IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae5582b8cb0b1c944c0c8a8f5322500f7a2bf264d7477a52497f44115f23f58 +size 2501393024 diff --git a/granite-3.0-8b-instruct.IQ3_XS.gguf b/granite-3.0-8b-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..09ab348 --- /dev/null +++ b/granite-3.0-8b-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88ea30691ec3570e906d9ad60b870e21e4a17dafa3367c2aee133b54a2287a8 +size 3428188384 diff --git a/granite-3.0-8b-instruct.IQ4_XS.gguf b/granite-3.0-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..095f2b5 --- /dev/null +++ b/granite-3.0-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7b6b355ec66a3d3a5373dff9b6313a216be8b1bdca78ba713fbaede777a111 +size 4428267744 diff --git a/granite-3.0-8b-instruct.Q2_K.gguf b/granite-3.0-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..bcc1662 --- /dev/null +++ b/granite-3.0-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8d53beaa4182c2c4d3b829419fa1d69f357ce61e24d7f167bff322dd2e2b6a +size 3103785184 diff --git a/granite-3.0-8b-instruct.Q3_K_L.gguf b/granite-3.0-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..77b1e9d --- /dev/null +++ b/granite-3.0-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dfbca9521db0bfe71d000231b7c81daf30458a5e45fe0dcbbd679ab2bf0bdf6 +size 4349624544 diff --git a/granite-3.0-8b-instruct.Q3_K_M.gguf b/granite-3.0-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..1fad60e --- /dev/null +++ b/granite-3.0-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedfa5f7e1961ed16d10a3dfaab53e1029883058bb8fe07bd92e98f685ff9280 +size 3996778720 diff --git a/granite-3.0-8b-instruct.Q3_K_S.gguf b/granite-3.0-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bb0bdd6 --- /dev/null +++ b/granite-3.0-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fad2248f7a0d0e370c4e0cbae464e4d2f902c3da1f4c26820cfcf5b2d38b8ff +size 3592683744 diff --git a/granite-3.0-8b-instruct.Q4_K_M.gguf b/granite-3.0-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..5fe48b8 --- /dev/null +++ b/granite-3.0-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd27b436494ecd76e83d28359ca4ee1fe8048985b64832b09eda562971dd8a1 +size 4943053024 diff --git a/granite-3.0-8b-instruct.Q4_K_S.gguf b/granite-3.0-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..145cabf --- /dev/null +++ b/granite-3.0-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4312936d7a8d0dcb0f00847d8ea443e6f6fbcf8cb746731ca1bce6e6a90db4fd +size 4685955296 diff --git a/granite-3.0-8b-instruct.Q5_K_M.gguf b/granite-3.0-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..e111810 --- /dev/null +++ b/granite-3.0-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a253406a64c09bf195bafe3f5ccc7262c4bec84c0c98d7557b998f3d172cd99 +size 5797642464 diff --git a/granite-3.0-8b-instruct.Q5_K_S.gguf b/granite-3.0-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8f98a6d --- /dev/null +++ b/granite-3.0-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934651e7cad73c0dbd93a99242e3c5cb273f4a93433169d567cd08deec68da1b +size 5647237344 diff --git a/granite-3.0-8b-instruct.Q6_K.gguf b/granite-3.0-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..d15076f --- /dev/null +++ b/granite-3.0-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e4781ca0ff1823bacd80f8c5219ec41d3ec0fdf31386012015943b8a0671a3f +size 6705643744 diff --git a/granite-3.0-8b-instruct.Q8_0.gguf b/granite-3.0-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..60b09ac --- /dev/null +++ b/granite-3.0-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75194c770d8872f8a95279c56f034a9a1f50b4a785e950d05f14187602b236c +size 8684440704 diff --git a/granite-3.0-8b-instruct.fp16.gguf b/granite-3.0-8b-instruct.fp16.gguf new file mode 100644 index 0000000..1de971a --- /dev/null +++ b/granite-3.0-8b-instruct.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2459211039691b6861ed11c020b238be114681377aad8260c1687c892cf2a7 +size 16344299648