commit 2b34e3c90242bba0e6306971d266c412a704840e Author: ModelHub XC Date: Tue Aug 25 17:16:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..57a7d43 --- /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 + +Llama-3-8B-Instruct-v0.9.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.fp16.gguf filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Llama-3-8B-Instruct-v0.9.IQ1_M.gguf b/Llama-3-8B-Instruct-v0.9.IQ1_M.gguf new file mode 100644 index 0000000..faf02fc --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80de588728e00ceb3117dee6ae9c1d3a03afcfcd0ed2558350486d29bd7f25bc +size 2161971840 diff --git a/Llama-3-8B-Instruct-v0.9.IQ1_S.gguf b/Llama-3-8B-Instruct-v0.9.IQ1_S.gguf new file mode 100644 index 0000000..ac4eab0 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80caf2ae1572e9d72482fc8a210f19c859ef100515e2df955f3509b12cc4c82b +size 2019627648 diff --git a/Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf b/Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf new file mode 100644 index 0000000..d112b36 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e421f5b8d74daf9d192e436ed15bdf98be6800e2d212c2e5e476341089d009d3 +size 2605781632 diff --git a/Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf b/Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf new file mode 100644 index 0000000..79eb5b5 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717a28c28f2c4089f5bf51ae9e3d3a9403077bf059bb4888abf9a9bb0b7c6b3a +size 3518747264 diff --git a/Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf b/Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf new file mode 100644 index 0000000..bb3d880 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6824febff2ce530ec181950925d54c3b66ebccfd54b4fb034cc012c0aadc584d +size 4447662720 diff --git a/Llama-3-8B-Instruct-v0.9.Q2_K.gguf b/Llama-3-8B-Instruct-v0.9.Q2_K.gguf new file mode 100644 index 0000000..35294e0 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:290065572d465e29ece31db1059d89227c8e60f87836d78080722bc7f8ea696e +size 3179131520 diff --git a/Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf b/Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf new file mode 100644 index 0000000..74401e4 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e4a69e090a68b6f8b57fbf0be5222464a9dc1fa8167ddeff8f6fc753f28001 +size 4321956480 diff --git a/Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf b/Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf new file mode 100644 index 0000000..ec96715 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33be3084702ebfec9349b250d18c36e86e57bebb7da687fb20a6bb81b84bd57 +size 4018918016 diff --git a/Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf b/Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf new file mode 100644 index 0000000..25a9b88 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4caf546b0019b4113f6b2183bffccba9c4678876c02622683fcd941103b220 +size 3664499328 diff --git a/Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf b/Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf new file mode 100644 index 0000000..c1490bf --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8141d0457d732c59ecdcb8bf847ae8267264ea4123059ed04310154ec2900c9 +size 4920734336 diff --git a/Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf b/Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf new file mode 100644 index 0000000..c799109 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfa9e1a1c1893a1bff3b065a4610992d7098b632e7a1af109f5e1ea838d74d7 +size 4692669056 diff --git a/Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf b/Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf new file mode 100644 index 0000000..f0028bb --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:730731c0d2b42ff4389685d19804e6d520364aa0164f2f400be60bf04f48a1c8 +size 5732987520 diff --git a/Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf b/Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf new file mode 100644 index 0000000..8f81c6d --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdfa78275f533c70fcf6364b56aca79926bf436deaec7716f6f02948266a64e6 +size 5599294080 diff --git a/Llama-3-8B-Instruct-v0.9.Q6_K.gguf b/Llama-3-8B-Instruct-v0.9.Q6_K.gguf new file mode 100644 index 0000000..490cbb4 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24e94ff1b4cb379eb1e785ea1e628b2d98996d2c3440aea83a8f5c3ceba5c00b +size 6596006528 diff --git a/Llama-3-8B-Instruct-v0.9.Q8_0.gguf b/Llama-3-8B-Instruct-v0.9.Q8_0.gguf new file mode 100644 index 0000000..c1ab7ba --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49432a0da4c0414c3f30b2547a19f12f997e728d11b3f1c8839fa5f3a1fd6521 +size 8540770944 diff --git a/Llama-3-8B-Instruct-v0.9.fp16.gguf b/Llama-3-8B-Instruct-v0.9.fp16.gguf new file mode 100644 index 0000000..2c1d428 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.9.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b26ad86ef7e38824425fbc0615d9d5b4f8254807789b3c8c329503605aaa6db +size 16068891072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f6159f --- /dev/null +++ b/README.md @@ -0,0 +1,48 @@ +--- +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +- llama-3 +- llama +- text-generation +model_name: Llama-3-8B-Instruct-v0.9-GGUF +base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9 +inference: false +model_creator: MaziyarPanahi +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +--- +# [MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF) +- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi) +- Original model: [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9) + +## Description +[MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF) contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9). + +### 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..bea82e8 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d91dde1599bc4a2d088cfc43cb2c6507849a6ffa384f6a7444a44d9da1ad800 +size 4988146