初始化项目，由ModelHub XC社区提供模型

Model: MaziyarPanahi/Llama3.1-8B-Chinese-Chat-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,52 @@
+*.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
+Llama3.1-8B-Chinese-Chat.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.fp16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Llama3.1-8B-Chinese-Chat.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text

Llama3.1-8B-Chinese-Chat-GGUF_imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af21259a0798374ddc9440ce329678a5a6a0833a73df51a386baf07e6fcd403
+size 4988146

Llama3.1-8B-Chinese-Chat.IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e09cb3c6009c89813edb7f0ba1abb5422324044f51d2e51efc1b4334a72783
+size 2161972672

Llama3.1-8B-Chinese-Chat.IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e702282da3627feae438e197556052233ce07f7b713e34d3c4da185b4a5591af
+size 2019628480

Llama3.1-8B-Chinese-Chat.IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5b661541e74669d6a9bcc68b4f68520bec3c2b1e734318f956751e99cf0636
+size 2605782464

Llama3.1-8B-Chinese-Chat.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61cfd83c8ea05b0ec3cfa942ea0f94f11bf68ccf4db1483615b1e8b4b6138d8
+size 3518748096

Llama3.1-8B-Chinese-Chat.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0053ee7b7ef7feea9bf61dc69f8898cc137935b074b0e1c542568be61f0cc88c
+size 4447663552

Llama3.1-8B-Chinese-Chat.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497d71c29791f8bbe1cabd32a27cad069dbdce4ae84f14f9786a52dc526d370e
+size 3179132352

Llama3.1-8B-Chinese-Chat.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4dcd4aa4fb077403c06941c904166401ae26c35c46385b0c0cd67c8e01219db
+size 4321957312

Llama3.1-8B-Chinese-Chat.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553c6f22db73ad8f48c50c08b11eb4ea04f339474a7870172f27cf12db02bdba
+size 4018918848

Llama3.1-8B-Chinese-Chat.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1531a5f67c9bdaccfde7d6b8d7f3795085697fb0a1360d5c6c1ccfd8836e95d7
+size 3664500160

Llama3.1-8B-Chinese-Chat.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bcb49c9c3054938ab567fd54fa6287903a78ab606fdb7852b8f9d864ac621f3
+size 4920735168

Llama3.1-8B-Chinese-Chat.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632d729d0edb0117065637014b9d67316a7f22efcea58bcf62f189f67ae9b051
+size 4692669888

Llama3.1-8B-Chinese-Chat.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6105773a6e4c601efb6246bd7a28ef4d994c69e2dce20815879f999909943b2d
+size 5732988352

Llama3.1-8B-Chinese-Chat.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19970c797b5f2de9fb34b418ed677e86141b06282b9284b562fc1c6581c63ccb
+size 5599294912

Llama3.1-8B-Chinese-Chat.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8684a364530b93001a65b196d4c3923916c4b3eb9340eb9308f06f2b3c7c7e6e
+size 6596007360

Llama3.1-8B-Chinese-Chat.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece27d98f4591fe7293c8a511c0f54a9d27fd12ce630f8c9528ca4deedfd7c28
+size 8540771776

Llama3.1-8B-Chinese-Chat.fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6167b1d4e55e370646992a72c2be4b32088e452bc3b2bc26a983fb816d96b6f6
+size 16068891872

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: Llama3.1-8B-Chinese-Chat-GGUF
+base_model: shenzhi-wang/Llama3.1-8B-Chinese-Chat
+inference: false
+model_creator: shenzhi-wang
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# [MaziyarPanahi/Llama3.1-8B-Chinese-Chat-GGUF](https://huggingface.co/MaziyarPanahi/Llama3.1-8B-Chinese-Chat-GGUF)
+- Model creator: [shenzhi-wang](https://huggingface.co/shenzhi-wang)
+- Original model: [shenzhi-wang/Llama3.1-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3.1-8B-Chinese-Chat)
+
+## Description
+[MaziyarPanahi/Llama3.1-8B-Chinese-Chat-GGUF](https://huggingface.co/MaziyarPanahi/Llama3.1-8B-Chinese-Chat-GGUF) contains GGUF format model files for [shenzhi-wang/Llama3.1-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3.1-8B-Chinese-Chat).
+
+### 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.

config.json

@@ -0,0 +1,3 @@
+{
+    "model_type": "mistral"
+}