commit 464d945661e81905f2ef3e0150651cdb695a0f2a Author: ModelHub XC Date: Sat Sep 5 18:55:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Swahili-Instruct-V2-3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fcde1dc --- /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 +Swahili-Instruct-V2-3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Swahili-Instruct-V2-3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b53ab3 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: GodsonNtungi/Swahili-Instruct-V2-3 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/GodsonNtungi/Swahili-Instruct-V2-3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Swahili-Instruct-V2-3-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/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Swahili-Instruct-V2-3-GGUF/resolve/main/Swahili-Instruct-V2-3.f16.gguf) | f16 | 14.6 | 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. + + diff --git a/Swahili-Instruct-V2-3.IQ4_XS.gguf b/Swahili-Instruct-V2-3.IQ4_XS.gguf new file mode 100644 index 0000000..7d31b25 --- /dev/null +++ b/Swahili-Instruct-V2-3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8790bd880fd1480e5c4a09b7a3166bfb1dc2e09103a01d9021ff4ae6526508 +size 3944390208 diff --git a/Swahili-Instruct-V2-3.Q2_K.gguf b/Swahili-Instruct-V2-3.Q2_K.gguf new file mode 100644 index 0000000..709815d --- /dev/null +++ b/Swahili-Instruct-V2-3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a110c4c1c50bb5f0d6d224fd7f4536e503b990223078d0be23d4e96b8c7d1527 +size 2719243840 diff --git a/Swahili-Instruct-V2-3.Q3_K_L.gguf b/Swahili-Instruct-V2-3.Q3_K_L.gguf new file mode 100644 index 0000000..8723379 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8739ec77d6b24b3ddb9f54fdee8dd69319f645b8d6bd271c8f2f3c4f7b1d7c23 +size 3822026304 diff --git a/Swahili-Instruct-V2-3.Q3_K_M.gguf b/Swahili-Instruct-V2-3.Q3_K_M.gguf new file mode 100644 index 0000000..89a73c6 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea94f12efb8b97e6e69d09835d25471a34614b2fbc8b2785c950f837a2aac23 +size 3518987840 diff --git a/Swahili-Instruct-V2-3.Q3_K_S.gguf b/Swahili-Instruct-V2-3.Q3_K_S.gguf new file mode 100644 index 0000000..dbf2320 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d4a20cc8c29a7b1494be01eea4f2f3b36881c034c4bbc154cbd3bd85c2d9c7 +size 3164569152 diff --git a/Swahili-Instruct-V2-3.Q4_K_M.gguf b/Swahili-Instruct-V2-3.Q4_K_M.gguf new file mode 100644 index 0000000..6e1eca0 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834ad1a098168b1f8ce2a8e749235f9413d3e755ed0696fc5045c40922026a12 +size 4368440896 diff --git a/Swahili-Instruct-V2-3.Q4_K_S.gguf b/Swahili-Instruct-V2-3.Q4_K_S.gguf new file mode 100644 index 0000000..a275996 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c206a9d4c88e9c815e90713ed45829098bd2ef74c7b24486e6512a694dcd8de1 +size 4140375616 diff --git a/Swahili-Instruct-V2-3.Q5_K_M.gguf b/Swahili-Instruct-V2-3.Q5_K_M.gguf new file mode 100644 index 0000000..8aefa36 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3563dc9daf2a49a22f8c7bff67a8591bc6b21d351523b15df634d60e5b9fc8ce +size 5131411008 diff --git a/Swahili-Instruct-V2-3.Q5_K_S.gguf b/Swahili-Instruct-V2-3.Q5_K_S.gguf new file mode 100644 index 0000000..826cacd --- /dev/null +++ b/Swahili-Instruct-V2-3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ec6623dcb6063ae13176d377165d76263d697fee3b8bd45fb67d10a6e1d441 +size 4997717568 diff --git a/Swahili-Instruct-V2-3.Q6_K.gguf b/Swahili-Instruct-V2-3.Q6_K.gguf new file mode 100644 index 0000000..0d6cec5 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b1827f0aa25b24b1b761c9037918e9293c6ffa63a2f80198329cb4f8653a100 +size 5942066752 diff --git a/Swahili-Instruct-V2-3.Q8_0.gguf b/Swahili-Instruct-V2-3.Q8_0.gguf new file mode 100644 index 0000000..402f0f7 --- /dev/null +++ b/Swahili-Instruct-V2-3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085240f1c7912d116d1ed936df6a93babcfa01901e079cfa66a8fc21221c8894 +size 7695859264 diff --git a/Swahili-Instruct-V2-3.f16.gguf b/Swahili-Instruct-V2-3.f16.gguf new file mode 100644 index 0000000..80f3fbd --- /dev/null +++ b/Swahili-Instruct-V2-3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a77b595631c3b99e240b5ca4ff32257591408849c8825d0c0455909669e0638 +size 14484733504