commit e6ea9e318481b29f07c23b7ac1f061f5bace91d8 Author: ModelHub XC Date: Sat May 9 21:47:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Arabic-llama3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4180c34 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Arabic-llama3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Arabic-llama3.i1-IQ1_M.gguf b/Arabic-llama3.i1-IQ1_M.gguf new file mode 100644 index 0000000..305b1d3 --- /dev/null +++ b/Arabic-llama3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4714f46c3cdf9d30046234d7ccf4dee07ef7db6802808eaf499bcc774e7b796c +size 2161972736 diff --git a/Arabic-llama3.i1-IQ1_S.gguf b/Arabic-llama3.i1-IQ1_S.gguf new file mode 100644 index 0000000..4213488 --- /dev/null +++ b/Arabic-llama3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e617f68b4ec7301a02ef617f23fc6225f0fac3d8d3a5f698f6e8ad1b528ba60e +size 2019628544 diff --git a/Arabic-llama3.i1-IQ2_M.gguf b/Arabic-llama3.i1-IQ2_M.gguf new file mode 100644 index 0000000..f184de1 --- /dev/null +++ b/Arabic-llama3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19311dd4445aaeb432112d65fe47bb99bab7444e2275e94121c712e29a7aa7b8 +size 2948281856 diff --git a/Arabic-llama3.i1-IQ2_S.gguf b/Arabic-llama3.i1-IQ2_S.gguf new file mode 100644 index 0000000..b7c682a --- /dev/null +++ b/Arabic-llama3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34e3b357d0872e2b9bcb431f91c965057c178ae55064fa7936483290756c99e +size 2758489600 diff --git a/Arabic-llama3.i1-IQ2_XS.gguf b/Arabic-llama3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..99dbb99 --- /dev/null +++ b/Arabic-llama3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10c4f0b04edbd12e3c41c536a840bc137ffb746f304b9e13144c388b2055101 +size 2605782528 diff --git a/Arabic-llama3.i1-IQ2_XXS.gguf b/Arabic-llama3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3150dba --- /dev/null +++ b/Arabic-llama3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2530848a3b8e3c20d5966e82bc2be184e4b79cbb11c9f192ddb77730edeb51 +size 2399213056 diff --git a/Arabic-llama3.i1-IQ3_M.gguf b/Arabic-llama3.i1-IQ3_M.gguf new file mode 100644 index 0000000..094fa40 --- /dev/null +++ b/Arabic-llama3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd5e7eb85ed648158cedb72f1d1b88d3ba60016a6766c10840ad12f5b0f96eb +size 3784824320 diff --git a/Arabic-llama3.i1-IQ3_S.gguf b/Arabic-llama3.i1-IQ3_S.gguf new file mode 100644 index 0000000..e1fd3cf --- /dev/null +++ b/Arabic-llama3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50dc5973e8959e698aac74cf63956fcd419de23220f77b407430835c3fd26dd +size 3682326016 diff --git a/Arabic-llama3.i1-IQ3_XS.gguf b/Arabic-llama3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..55ca62f --- /dev/null +++ b/Arabic-llama3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41a811a6d78d361f696612e414f2eb6e0150ea7a610e1e787d92facc15eece9 +size 3518748160 diff --git a/Arabic-llama3.i1-IQ3_XXS.gguf b/Arabic-llama3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1b2012a --- /dev/null +++ b/Arabic-llama3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f08d6edd82f0f0ece5ef41ccb7da193a2ce8c588ecd12908fc84c14bce947ee +size 3274913280 diff --git a/Arabic-llama3.i1-IQ4_NL.gguf b/Arabic-llama3.i1-IQ4_NL.gguf new file mode 100644 index 0000000..9ca810a --- /dev/null +++ b/Arabic-llama3.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80b70f4f5fb477de5ad604b38a7c1d52b5709d5b07ef2701f1186ea0f58f1f1 +size 4677989888 diff --git a/Arabic-llama3.i1-IQ4_XS.gguf b/Arabic-llama3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ada898f --- /dev/null +++ b/Arabic-llama3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45a24459f99bc9c60168b638a89feb9beff0d212d3a4463f7fc0e70a9a0c7a8 +size 4447663616 diff --git a/Arabic-llama3.i1-Q2_K.gguf b/Arabic-llama3.i1-Q2_K.gguf new file mode 100644 index 0000000..679eb92 --- /dev/null +++ b/Arabic-llama3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e17de0f716b9a7a9494050681f9b4e0ef7b574be8fb998499decc98b6fcdbc +size 3179132416 diff --git a/Arabic-llama3.i1-Q2_K_S.gguf b/Arabic-llama3.i1-Q2_K_S.gguf new file mode 100644 index 0000000..79a8c30 --- /dev/null +++ b/Arabic-llama3.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ad7bf9cc79293ea4796d9192e17162880264927ed1e89a11b810cdf676cfcc +size 2988815872 diff --git a/Arabic-llama3.i1-Q3_K_L.gguf b/Arabic-llama3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e9b3fad --- /dev/null +++ b/Arabic-llama3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cae4c13ed121a6fc68d0271a289579de47b48dcd7d9fad72f9e8e6f192fb86c5 +size 4321957376 diff --git a/Arabic-llama3.i1-Q3_K_M.gguf b/Arabic-llama3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5c57d91 --- /dev/null +++ b/Arabic-llama3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4183460b0e93b62d9d99a06be67cdf75a52270879d020b47be1df0b66657e8ad +size 4018918912 diff --git a/Arabic-llama3.i1-Q3_K_S.gguf b/Arabic-llama3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..aecf35b --- /dev/null +++ b/Arabic-llama3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ed679a9b78e76ecb0d6a11d006eda65f471c4db82f44227f88643177b1a80d +size 3664500224 diff --git a/Arabic-llama3.i1-Q4_0.gguf b/Arabic-llama3.i1-Q4_0.gguf new file mode 100644 index 0000000..4632d39 --- /dev/null +++ b/Arabic-llama3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebadd659c051eb4f3cbfb8a32e2d4601a428fff419ef9b7aff4acbdc2e503c9 +size 4675892736 diff --git a/Arabic-llama3.i1-Q4_1.gguf b/Arabic-llama3.i1-Q4_1.gguf new file mode 100644 index 0000000..47ed231 --- /dev/null +++ b/Arabic-llama3.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af91bbd229037dacc32dfaa2dd6ca52d421f8136e1b659dbdead4e9ea75d5daf +size 5130253824 diff --git a/Arabic-llama3.i1-Q4_K_M.gguf b/Arabic-llama3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f2dac38 --- /dev/null +++ b/Arabic-llama3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528ae24e72f31ad3e27b6d25975cdf112e88164a3c78929267099f602ee6ec61 +size 4920735232 diff --git a/Arabic-llama3.i1-Q4_K_S.gguf b/Arabic-llama3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1d1caa8 --- /dev/null +++ b/Arabic-llama3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbad9c96d764aa86e95401ee21631f66442a3840746b633da2b18bf4583691e4 +size 4692669952 diff --git a/Arabic-llama3.i1-Q5_K_M.gguf b/Arabic-llama3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a3753f2 --- /dev/null +++ b/Arabic-llama3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1a5efefff155d2fc353dba7751f7433947b250835b8b198ecf7e6484eb279a +size 5732988416 diff --git a/Arabic-llama3.i1-Q5_K_S.gguf b/Arabic-llama3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..862650d --- /dev/null +++ b/Arabic-llama3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4401a25a05adec4c61e695dcd5c019d0040d591bc09d39b4a2533c18a62342f3 +size 5599294976 diff --git a/Arabic-llama3.i1-Q6_K.gguf b/Arabic-llama3.i1-Q6_K.gguf new file mode 100644 index 0000000..43597f5 --- /dev/null +++ b/Arabic-llama3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0985d50488b932d4b2892acb172497d04d829f5bf0860fcb82f9e215986b06 +size 6596007424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..af1fe8f --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: HeshamHaroon/Arabic-llama3 +datasets: +- Yasbok/Alpaca_arabic_instruct +language: +- en +- ar +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/HeshamHaroon/Arabic-llama3 + + +static quants are available at https://huggingface.co/mradermacher/Arabic-llama3-GGUF +## 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/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arabic-llama3-i1-GGUF/resolve/main/Arabic-llama3.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ae7d489 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65407020a09243af838d7c4ab4095a4f6a80c00d20cd53e15d94a4ca6b30e143 +size 4988157