commit 661ba07d47a683094cb85051d1cfb13f2b9e34fb Author: ModelHub XC Date: Sun Aug 2 16:01:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..36a3e55 --- /dev/null +++ b/.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-3-Layers.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-3-Layers.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8b-Pruned-3-Layers.IQ3_M.gguf b/Llama-3.1-8b-Pruned-3-Layers.IQ3_M.gguf new file mode 100644 index 0000000..65fb76c --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2bd7229bb316c9c70e624b5f296327d9aaf7c72809ca3e87b6bd6543107e529 +size 3390884896 diff --git a/Llama-3.1-8b-Pruned-3-Layers.IQ3_S.gguf b/Llama-3.1-8b-Pruned-3-Layers.IQ3_S.gguf new file mode 100644 index 0000000..ef987e0 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35e2a91ddfdb89eb979229413d6c96fae61eaec2f9fc94c923229fd11b74466 +size 3305098272 diff --git a/Llama-3.1-8b-Pruned-3-Layers.IQ3_XS.gguf b/Llama-3.1-8b-Pruned-3-Layers.IQ3_XS.gguf new file mode 100644 index 0000000..c11e7a1 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a3070529307cfe91514f9c4375fa0c46f7f5d74c7ceaf4725fdf8b64b5f1b8 +size 3161967648 diff --git a/Llama-3.1-8b-Pruned-3-Layers.IQ4_XS.gguf b/Llama-3.1-8b-Pruned-3-Layers.IQ4_XS.gguf new file mode 100644 index 0000000..178ad37 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322bf85c052123eb42179fb707c239ea572f77a92357c770a3c07b90d2f32c1c +size 4008963104 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q2_K.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q2_K.gguf new file mode 100644 index 0000000..e25be7a --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c53929cc4d74d7a1630c54647e491afdc751ac1f171f2c9ae07d867fd1aa05 +size 2858134560 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q3_K_L.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q3_K_L.gguf new file mode 100644 index 0000000..1a26edd --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32b94b0241f52d5d714a48400448ad6df6950bbda007f794e08bc9cb17b5205 +size 3864775712 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q3_K_M.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q3_K_M.gguf new file mode 100644 index 0000000..5f654a1 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2fbeb995dcd306bf100de4d95d841fd83b2778545e00bdcbec1cec943115a1d +size 3594243104 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q3_K_S.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q3_K_S.gguf new file mode 100644 index 0000000..92d6443 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9e66b3a8beee7a39ed8cebf0c259453e23f780128c7d2153eab3cf624e7b057 +size 3289500704 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q4_K_M.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q4_K_M.gguf new file mode 100644 index 0000000..6545ba1 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2bb3d4622c259053df2aa11197000976f6ae70701a3855b93c8b73905f96a0a +size 4397427744 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q4_K_S.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q4_K_S.gguf new file mode 100644 index 0000000..32c7d78 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd52052150665ea6cf5555cff6bed4102a2add090670b43633ae91149b57823 +size 4194462752 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q5_K_M.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q5_K_M.gguf new file mode 100644 index 0000000..e60d33b --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826f31b041ac64b98c60951e16bfef2813a675f0f79c4a4bd7b814f0d42382ca +size 5116357664 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q5_K_S.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q5_K_S.gguf new file mode 100644 index 0000000..8c8e1fe --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0353b42960c5e2a075f771b0cfe15e1fb48d05cf843af2704c3544bd05cf1dd5 +size 4999375904 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q6_K.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q6_K.gguf new file mode 100644 index 0000000..f8205a3 --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75aba6037dec25a10e4495fc15c82264970ddcc253a59d97b6651381509831bb +size 5880220704 diff --git a/Llama-3.1-8b-Pruned-3-Layers.Q8_0.gguf b/Llama-3.1-8b-Pruned-3-Layers.Q8_0.gguf new file mode 100644 index 0000000..85e44fc --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a252b6dc3ea7e02a5c98a1c65e466df8ff9434eb045825c47cdbab1126ca99eb +size 7613697056 diff --git a/Llama-3.1-8b-Pruned-3-Layers.f16.gguf b/Llama-3.1-8b-Pruned-3-Layers.f16.gguf new file mode 100644 index 0000000..1e915ad --- /dev/null +++ b/Llama-3.1-8b-Pruned-3-Layers.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149de724c49ad3fb407f80c73bf213b5152467805a787c4f0786d0d7a5e6a7d1 +size 14323928096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b2ba09 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Na0s/Llama-3.1-8b-Pruned-3-Layers +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Na0s/Llama-3.1-8b-Pruned-3-Layers + + +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-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.IQ3_XS.gguf) | IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.IQ3_M.gguf) | IQ3_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q3_K_L.gguf) | Q3_K_L | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.Q8_0.gguf) | Q8_0 | 7.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-3-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-3-Layers.f16.gguf) | f16 | 14.4 | 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. + +