初始化项目，由ModelHub XC社区提供模型

Model: MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF
Source: Original Platform

.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-32k-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.fp16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-32k-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-Instruct-32k-v0.1.IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34c03b461404792ced4b72c922486ee171f71178880c97360cca2c6b680c8ea
+size 2161971712

Llama-3-8B-Instruct-32k-v0.1.IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fadff00eb34f9bb76641532a2df2c47fca5b1478a21535f33c83056cc5eede
+size 2019627520

Llama-3-8B-Instruct-32k-v0.1.IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d108c910997e2f8429f8929c165401a7f0804a1f60e37f3b4d3982af70a3bb
+size 2605781504

Llama-3-8B-Instruct-32k-v0.1.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e1d5bf9bad303bdd4870b36aa26ec3dd1c1d8b4304a2f8bac63d4b23814584
+size 3518747136

Llama-3-8B-Instruct-32k-v0.1.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dbadccb96b7aceefd5553d4c0877dac3cb3a52b57e36eda99f5a35f5f2db0d
+size 4447662592

Llama-3-8B-Instruct-32k-v0.1.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a28c971b03973dda3000c1b86eb255e7fb41465e2656d4582199d0964a21a4
+size 3179131392

Llama-3-8B-Instruct-32k-v0.1.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be524edc0602d0f1353da9eb55dd414fe7b8de2cbbab6cec4b3b5332d4eba74
+size 4321956352

Llama-3-8B-Instruct-32k-v0.1.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4204bf8376d1f5c2abdfadac84557aef7d06ed56efa173ad4badbc6a4687b4
+size 4018917888

Llama-3-8B-Instruct-32k-v0.1.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c23fc32107a5edf6bdabc832ca563c9ec6b6102d4cf8910e0600cb051746e3b
+size 3664499200

Llama-3-8B-Instruct-32k-v0.1.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce73ab970160293bf13a9c707f3bd973b49387ef5bc6681019afcc1ec42df6e2
+size 4920734208

Llama-3-8B-Instruct-32k-v0.1.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae85c66329cb71eb6db48d94039472ae10462120f38fffdef92d998aab166180
+size 4692668928

Llama-3-8B-Instruct-32k-v0.1.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553e6c15eac274589a9f7745fa4510cbdd8ce18d17f21481cb1123f60477ea47
+size 5732987392

Llama-3-8B-Instruct-32k-v0.1.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c41459f769670c9b9991df0c30771ecf0e8cd452031046b50bb01666b872bc
+size 5599293952

Llama-3-8B-Instruct-32k-v0.1.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1ea9441a3e3eed59473ab7c7388f47767d5fe9f61af747f576df6bb9bd9558
+size 6596006400

Llama-3-8B-Instruct-32k-v0.1.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66b88c6c85fe7e531ac850b472ba6445269d9d5d7f3dc687a9faa13a1b79afc
+size 8540770816

Llama-3-8B-Instruct-32k-v0.1.fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ffaa428dbdbbe480f51ad7315da7892f290964a2d422707ff590f54379332c4
+size 16068890944

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: Llama-3-8B-Instruct-32k-v0.1-GGUF
+base_model: MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1
+inference: false
+model_creator: MaziyarPanahi
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# [MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF)
+- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
+- Original model: [MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1)
+
+## Description
+[MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1).
+
+### 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"
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218829cbec9a6eaba368d228493f5fafcdb84d06b380d1679eb27c810a689e0d
+size 4988146