commit 0e6cbc28fcfe5151f961cf903205d83534dfb952 Author: ModelHub XC Date: Sat May 9 15:12:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-mono-Swahili-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b98cd7f --- /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-3-8B-mono-Swahili.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Swahili.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-mono-Swahili.IQ4_XS.gguf b/Llama-3-8B-mono-Swahili.IQ4_XS.gguf new file mode 100644 index 0000000..358e27c --- /dev/null +++ b/Llama-3-8B-mono-Swahili.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c664b0de04e1a68fd4022c95658777d63a1b277d99536b0c3ea53812faa35bc7 +size 4484363200 diff --git a/Llama-3-8B-mono-Swahili.Q2_K.gguf b/Llama-3-8B-mono-Swahili.Q2_K.gguf new file mode 100644 index 0000000..b3e080c --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac93d4cef9409c3383e1b1a362a4f0eccf1e5517e2815abf5a558cb42c102557 +size 3179131840 diff --git a/Llama-3-8B-mono-Swahili.Q3_K_L.gguf b/Llama-3-8B-mono-Swahili.Q3_K_L.gguf new file mode 100644 index 0000000..eb76475 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe049a2726d717e255b20c687c2e1f87bbc83e41e02f844e1bd9b798596c91d +size 4321956800 diff --git a/Llama-3-8B-mono-Swahili.Q3_K_M.gguf b/Llama-3-8B-mono-Swahili.Q3_K_M.gguf new file mode 100644 index 0000000..b86acd8 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30122ea2ca8bf5deed6407cd4b3809ba05b8897cd01263314f9a208218da9d15 +size 4018918336 diff --git a/Llama-3-8B-mono-Swahili.Q3_K_S.gguf b/Llama-3-8B-mono-Swahili.Q3_K_S.gguf new file mode 100644 index 0000000..b99d681 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03de8d0f89ebc25dc19215b47efacaf5898eeee7c9bd3923d36b75bcb0e85a57 +size 3664499648 diff --git a/Llama-3-8B-mono-Swahili.Q4_K_M.gguf b/Llama-3-8B-mono-Swahili.Q4_K_M.gguf new file mode 100644 index 0000000..3d11ad3 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0de518ee72a5c23ac7289f143a279b3fefd6d3b982a1d5a3e8ed28303a40820 +size 4920734656 diff --git a/Llama-3-8B-mono-Swahili.Q4_K_S.gguf b/Llama-3-8B-mono-Swahili.Q4_K_S.gguf new file mode 100644 index 0000000..ad90be4 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858e773e64d5469a7d508c2032070195f28b3b2265abba4b941eeb5270c173f5 +size 4692669376 diff --git a/Llama-3-8B-mono-Swahili.Q5_K_M.gguf b/Llama-3-8B-mono-Swahili.Q5_K_M.gguf new file mode 100644 index 0000000..6e74d12 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3dfe85d8f743fb247b2963a99d7d720ee94d2d1def1713c904ab0ead2aa02f2 +size 5732987840 diff --git a/Llama-3-8B-mono-Swahili.Q5_K_S.gguf b/Llama-3-8B-mono-Swahili.Q5_K_S.gguf new file mode 100644 index 0000000..ab456cb --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e4b5a21b77958a3441600340daffb5b40346504b5a4a25ec52914bf6d8e08e +size 5599294400 diff --git a/Llama-3-8B-mono-Swahili.Q6_K.gguf b/Llama-3-8B-mono-Swahili.Q6_K.gguf new file mode 100644 index 0000000..2419036 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57fc3b9a6babe6b0ba6bf2194a269a739d87da3e94b9b9941463a6eb46f30637 +size 6596006848 diff --git a/Llama-3-8B-mono-Swahili.Q8_0.gguf b/Llama-3-8B-mono-Swahili.Q8_0.gguf new file mode 100644 index 0000000..3d8d103 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10387ea94d11f1ba84db0ec0a0fabc81264362a398a940eabe1bd8e49eecb39c +size 8540771264 diff --git a/Llama-3-8B-mono-Swahili.f16.gguf b/Llama-3-8B-mono-Swahili.f16.gguf new file mode 100644 index 0000000..43d4ef2 --- /dev/null +++ b/Llama-3-8B-mono-Swahili.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874ccfda79b0cc09be4b03cbcf36ebebf49d444218b2ad60505be8cd3dcf83c6 +size 16068891584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..94e73a9 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: almanach/Llama-3-8B-mono-Swahili +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/almanach/Llama-3-8B-mono-Swahili + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-mono-Swahili-GGUF).*** + +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-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Swahili-GGUF/resolve/main/Llama-3-8B-mono-Swahili.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. + +