commit 8e9b82c63d5cef7d67f826780c052d994f4d6b64 Author: ModelHub XC Date: Mon Aug 10 08:33:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-SARA-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1fd72df --- /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-3.2-SARA-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SARA-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-SARA-3b.IQ4_XS.gguf b/Llama-3.2-SARA-3b.IQ4_XS.gguf new file mode 100644 index 0000000..618fe06 --- /dev/null +++ b/Llama-3.2-SARA-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b29fe4599bb4f4382fb8962ca97a79f6ecd8df890521fe9e59c3016ea586bd1 +size 2050217088 diff --git a/Llama-3.2-SARA-3b.Q2_K.gguf b/Llama-3.2-SARA-3b.Q2_K.gguf new file mode 100644 index 0000000..6b39777 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097b859d780c09280f3cd43a5030c6ba993bb6907d856dc5ecf3c44f0bfdac48 +size 1493214336 diff --git a/Llama-3.2-SARA-3b.Q3_K_L.gguf b/Llama-3.2-SARA-3b.Q3_K_L.gguf new file mode 100644 index 0000000..304937b --- /dev/null +++ b/Llama-3.2-SARA-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc430a3a7ee71fe4601b7a4af1ca3d7b1fbd3615da3513b9ab0fa12fd4b7c9e1 +size 1984642176 diff --git a/Llama-3.2-SARA-3b.Q3_K_M.gguf b/Llama-3.2-SARA-3b.Q3_K_M.gguf new file mode 100644 index 0000000..2e0d47e --- /dev/null +++ b/Llama-3.2-SARA-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7fd069abc96475af83bc0fd80f112c569d44ddc011b89f4fd10ee8a4ae3ddb +size 1856453760 diff --git a/Llama-3.2-SARA-3b.Q3_K_S.gguf b/Llama-3.2-SARA-3b.Q3_K_S.gguf new file mode 100644 index 0000000..5deb314 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba56e7ebe9d113f9e8a8bb40e91829a9a363a018ebabd548d7f9c265322d57fd +size 1712143488 diff --git a/Llama-3.2-SARA-3b.Q4_K_M.gguf b/Llama-3.2-SARA-3b.Q4_K_M.gguf new file mode 100644 index 0000000..372b573 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87fc478ab7a5d41f25edecda738142e0186ad632d22c7a0f13793f6203fe1cdc +size 2241000576 diff --git a/Llama-3.2-SARA-3b.Q4_K_S.gguf b/Llama-3.2-SARA-3b.Q4_K_S.gguf new file mode 100644 index 0000000..f4da9a2 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7f9fcbd83752e4c3cc828a74a4895ecfa5054bafbf171d9799f4bdd98728e7 +size 2149823616 diff --git a/Llama-3.2-SARA-3b.Q5_K_M.gguf b/Llama-3.2-SARA-3b.Q5_K_M.gguf new file mode 100644 index 0000000..6b04a85 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d3deef1651e15cd96f60a1c729cc060a875a01a6b0a64a7112ba47e3f37174 +size 2593027200 diff --git a/Llama-3.2-SARA-3b.Q5_K_S.gguf b/Llama-3.2-SARA-3b.Q5_K_S.gguf new file mode 100644 index 0000000..4e38b54 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353dc4fe4bbf5b1e02fda44502dd68f9c028c966f4e7036bbcd8add25f3c71ff +size 2540385408 diff --git a/Llama-3.2-SARA-3b.Q6_K.gguf b/Llama-3.2-SARA-3b.Q6_K.gguf new file mode 100644 index 0000000..f28e68f --- /dev/null +++ b/Llama-3.2-SARA-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0d7aa9f6fa6d089f9bba95886d44bd19ab5b21976c9e0d1d697be1014c975c +size 2967055488 diff --git a/Llama-3.2-SARA-3b.Q8_0.gguf b/Llama-3.2-SARA-3b.Q8_0.gguf new file mode 100644 index 0000000..c8f3318 --- /dev/null +++ b/Llama-3.2-SARA-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a1ff7bd67264491e20144b6b0e9876fed4fabeefa887a8adb4a1a457a82152 +size 3840523392 diff --git a/Llama-3.2-SARA-3b.f16.gguf b/Llama-3.2-SARA-3b.f16.gguf new file mode 100644 index 0000000..1b3d5ab --- /dev/null +++ b/Llama-3.2-SARA-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed7dcadc9354e8578bf683c86d53e0d5ba406f90be4baa7442fa6df7604ecbb4 +size 7221689472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e3edf05 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: EryriLabs/Llama-3.2-SARA-3b +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/EryriLabs/Llama-3.2-SARA-3b + + +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-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SARA-3b-GGUF/resolve/main/Llama-3.2-SARA-3b.f16.gguf) | f16 | 7.3 | 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. + +