初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,50 @@
+*.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
+Llama-3.1-8b-Pruned-5-Layers.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8b-Pruned-5-Layers.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.1-8b-Pruned-5-Layers.IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6c60f641fdf4d75ebbacaaeac98a9de4fa07b0d2f2d187dd7a52f01ac0ef16
+size 3197814784

Llama-3.1-8b-Pruned-5-Layers.IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a3532ba7b07b0c5ced3b6efdec2d64d93a30186d814897ccb095a2f2ca60e0
+size 3116484608

Llama-3.1-8b-Pruned-5-Layers.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7259b4324bd048f48bd0ee9d3faa9c3c26e942570af83af6d7497c87bbaf03c
+size 2986330112

Llama-3.1-8b-Pruned-5-Layers.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4648c0d93d48a7d773366416b679824f17d3fca0f2afb8036efd63ccb95712a3
+size 3775850496

Llama-3.1-8b-Pruned-5-Layers.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e96c9713442ae5a06007dee549ec5b35ea2e48663e53123b7fa931411f6b8d1
+size 2697635840

Llama-3.1-8b-Pruned-5-Layers.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b806ced126f992fdf980386cfb5ee7cebe81caff1b80ccac4f2112c802dbcc
+size 3636185088

Llama-3.1-8b-Pruned-5-Layers.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589e78c23ca24630fa5066e1fa8a6e6dcd0cad6f8f93a87bd54b48135a02fb10
+size 3385575424

Llama-3.1-8b-Pruned-5-Layers.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f68e3b4aaa342c77e0ec14dc74b981561f415c5425979773e5313d9476e663e
+size 3102001152

Llama-3.1-8b-Pruned-5-Layers.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3586b7377350d5465e986b399654f9279301211c5a010de038eb2a3f6fa191b0
+size 4135774208

Llama-3.1-8b-Pruned-5-Layers.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5cb33a10d3a7879e3c1b2c71f73e77277ad831d389b6b690cc85f9904e599d
+size 3949029376

Llama-3.1-8b-Pruned-5-Layers.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b7a642fa15265fe569fda394b7167eddf24df39c3e790682807b6f2898a43a
+size 4808042496

Llama-3.1-8b-Pruned-5-Layers.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3cef5d8f776ee684001d92bb675b913ba386d4fcae918657c34a6d8930a90f
+size 4699416576

Llama-3.1-8b-Pruned-5-Layers.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9569550625104a18b0ca70b4dad06994dfc36fc49d321304a76c4342a065b7
+size 5522327552

Llama-3.1-8b-Pruned-5-Layers.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19665839201d69e7e9c3a21f5700fe1a9ec6f087dbac01eb84ecb43011cc3406
+size 7150159872

Llama-3.1-8b-Pruned-5-Layers.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d51fcdec31c08312682f27c585b733a8f99b33cc5e514efdbf1d0d6f8f8922
+size 13451446272

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Na0s/Llama-3.1-8b-Pruned-5-Layers
+language:
+- en
+library_name: transformers
+quantized_by: mradermacher
+tags:
+- mergekit
+- merge
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags:  -->
+static quants of https://huggingface.co/Na0s/Llama-3.1-8b-Pruned-5-Layers
+
+<!-- provided-files -->
+weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
+## Usage
+
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+
+## Provided Quants
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q2_K.gguf) | Q2_K | 2.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.IQ3_XS.gguf) | IQ3_XS | 3.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q3_K_S.gguf) | Q3_K_S | 3.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.IQ3_S.gguf) | IQ3_S | 3.2 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.IQ3_M.gguf) | IQ3_M | 3.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q3_K_L.gguf) | Q3_K_L | 3.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.IQ4_XS.gguf) | IQ4_XS | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q5_K_S.gguf) | Q5_K_S | 4.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q5_K_M.gguf) | Q5_K_M | 4.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-5-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-5-Layers.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
+
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
+## FAQ / Model Request
+
+See https://huggingface.co/mradermacher/model_requests for some answers to
+questions you might have and/or if you want some other model quantized.
+
+## Thanks
+
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time.
+
+<!-- end -->