commit 9029d895c0125538ce25ec0ecf4f9fed2a47794e Author: ModelHub XC Date: Sat Jun 6 21:07:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-arabic-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..460df88 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-arabic-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-arabic-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..67e8e32 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: ModelsLab/llama-3.1-arabic-8b +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ModelsLab/llama-3.1-arabic-8b + + +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-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-arabic-8b-GGUF/resolve/main/llama-3.1-arabic-8b.f16.gguf) | f16 | 16.2 | 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. + + diff --git a/llama-3.1-arabic-8b.IQ4_XS.gguf b/llama-3.1-arabic-8b.IQ4_XS.gguf new file mode 100644 index 0000000..6d0bd46 --- /dev/null +++ b/llama-3.1-arabic-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5c00a8eb51ce0b03d2940c7871e898b890bae85e0abdc70bb18d6c4429f193 +size 4484363104 diff --git a/llama-3.1-arabic-8b.Q2_K.gguf b/llama-3.1-arabic-8b.Q2_K.gguf new file mode 100644 index 0000000..d719840 --- /dev/null +++ b/llama-3.1-arabic-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abfd48b41a0fd5e4d44fb3cb9b5f922553bf662676ec709a6c9c98b9b114b12 +size 3179131744 diff --git a/llama-3.1-arabic-8b.Q3_K_L.gguf b/llama-3.1-arabic-8b.Q3_K_L.gguf new file mode 100644 index 0000000..b6cd300 --- /dev/null +++ b/llama-3.1-arabic-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d5f860ec2515548431c178e6c5d2b64a19f4c877fdf7e086571acd93c73abf +size 4321956704 diff --git a/llama-3.1-arabic-8b.Q3_K_M.gguf b/llama-3.1-arabic-8b.Q3_K_M.gguf new file mode 100644 index 0000000..a52b695 --- /dev/null +++ b/llama-3.1-arabic-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ca3aaed50359c76ee6a03ebf2ca6b1bcbd0060886ef3570d4f1eb33f6f43b4 +size 4018918240 diff --git a/llama-3.1-arabic-8b.Q3_K_S.gguf b/llama-3.1-arabic-8b.Q3_K_S.gguf new file mode 100644 index 0000000..ee5a752 --- /dev/null +++ b/llama-3.1-arabic-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5b1e345cb1b68e1d5f9aa61b9e4486f297aed0de596a579afe5313df5ba5ce +size 3664499552 diff --git a/llama-3.1-arabic-8b.Q4_K_M.gguf b/llama-3.1-arabic-8b.Q4_K_M.gguf new file mode 100644 index 0000000..d16ce37 --- /dev/null +++ b/llama-3.1-arabic-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40ed31a00780c348ab9f5fceda2da8d4da5afdcd8d854cbb974eb7fc8d04d73 +size 4920734560 diff --git a/llama-3.1-arabic-8b.Q4_K_S.gguf b/llama-3.1-arabic-8b.Q4_K_S.gguf new file mode 100644 index 0000000..2191b55 --- /dev/null +++ b/llama-3.1-arabic-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74bd383cac47f84e3b6f6e775d5ea662f76d6b86227ea505bd28afe304041948 +size 4692669280 diff --git a/llama-3.1-arabic-8b.Q5_K_M.gguf b/llama-3.1-arabic-8b.Q5_K_M.gguf new file mode 100644 index 0000000..07252a0 --- /dev/null +++ b/llama-3.1-arabic-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd43156396fb1ca96291d63720cb92caa1338cce19c1f787ac894549521cf36 +size 5732987744 diff --git a/llama-3.1-arabic-8b.Q5_K_S.gguf b/llama-3.1-arabic-8b.Q5_K_S.gguf new file mode 100644 index 0000000..657ca0f --- /dev/null +++ b/llama-3.1-arabic-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165ef447cafaf5742bd4895467aa2a7c938ff1030d998b205101b5e4a52516f4 +size 5599294304 diff --git a/llama-3.1-arabic-8b.Q6_K.gguf b/llama-3.1-arabic-8b.Q6_K.gguf new file mode 100644 index 0000000..0dce595 --- /dev/null +++ b/llama-3.1-arabic-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fee67b85dc30b839e81f317bb78b19f80bce4f74d9270e6993c590184102584 +size 6596006752 diff --git a/llama-3.1-arabic-8b.Q8_0.gguf b/llama-3.1-arabic-8b.Q8_0.gguf new file mode 100644 index 0000000..82b4c55 --- /dev/null +++ b/llama-3.1-arabic-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb30e9e30dc38f76b500167af2d4756cc441bc227cc14251018c4513b7408b4 +size 8540771168 diff --git a/llama-3.1-arabic-8b.f16.gguf b/llama-3.1-arabic-8b.f16.gguf new file mode 100644 index 0000000..49977b6 --- /dev/null +++ b/llama-3.1-arabic-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f433c4193b0a08e46850e2893bf4aab06dfa90cea3c2a07a8ebc7d486371946 +size 16068891488