commit 2f34ba60e267aacb5707a1016de6eb8a4626e5a9 Author: ModelHub XC Date: Wed Sep 23 22:37:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SageLlama-3.1-8B-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a893b7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +SageLlama-3.1-8B-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9fab58b --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: pascarujo/SageLlama-3.1-8B-v3 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/pascarujo/SageLlama-3.1-8B-v3 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-i1-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/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-v3-GGUF/resolve/main/SageLlama-3.1-8B-v3.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/SageLlama-3.1-8B-v3.IQ3_M.gguf b/SageLlama-3.1-8B-v3.IQ3_M.gguf new file mode 100644 index 0000000..50ea2d6 --- /dev/null +++ b/SageLlama-3.1-8B-v3.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07542cc3f4b3126192509931a1c75e085e71d75824f85e91cde34473127e407e +size 3784824416 diff --git a/SageLlama-3.1-8B-v3.IQ3_S.gguf b/SageLlama-3.1-8B-v3.IQ3_S.gguf new file mode 100644 index 0000000..ede7d3f --- /dev/null +++ b/SageLlama-3.1-8B-v3.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff65d4f3adf1ff3c9ebd5b028256665ba4b80e459f314f24dc90ec7c61644b5 +size 3682326112 diff --git a/SageLlama-3.1-8B-v3.IQ3_XS.gguf b/SageLlama-3.1-8B-v3.IQ3_XS.gguf new file mode 100644 index 0000000..1c8d657 --- /dev/null +++ b/SageLlama-3.1-8B-v3.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769ee0fd148e6c611620ad787370f1ad3bda970ce58b44b6f7708da6422b5ab8 +size 3518748256 diff --git a/SageLlama-3.1-8B-v3.IQ4_XS.gguf b/SageLlama-3.1-8B-v3.IQ4_XS.gguf new file mode 100644 index 0000000..8659ebb --- /dev/null +++ b/SageLlama-3.1-8B-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:082126acd67359635eca02a55135e475c11ebe95da68ceefc9fe8b0c58f2660e +size 4484363872 diff --git a/SageLlama-3.1-8B-v3.Q2_K.gguf b/SageLlama-3.1-8B-v3.Q2_K.gguf new file mode 100644 index 0000000..1513ff0 --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79059f0dee679b98a625e7d607a3d4f1f8e02b9ae14d357dc9660ca90640e4d5 +size 3179132512 diff --git a/SageLlama-3.1-8B-v3.Q3_K_L.gguf b/SageLlama-3.1-8B-v3.Q3_K_L.gguf new file mode 100644 index 0000000..2d2d535 --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d054ad4619ded8d2057a9d3e6a2eec77f4f53d1acbaddfc4bf872e3be517d1b3 +size 4321957472 diff --git a/SageLlama-3.1-8B-v3.Q3_K_M.gguf b/SageLlama-3.1-8B-v3.Q3_K_M.gguf new file mode 100644 index 0000000..72741ad --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a82321711d9b3f3fa169dde9b6fcc24385bf401e6b3cd4ab6e58d9e334788f2c +size 4018919008 diff --git a/SageLlama-3.1-8B-v3.Q3_K_S.gguf b/SageLlama-3.1-8B-v3.Q3_K_S.gguf new file mode 100644 index 0000000..1f7b15c --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc1d12829513cfa29efcb86fbcc6946a421b1b93fee6a7b042a8be879f49989 +size 3664500320 diff --git a/SageLlama-3.1-8B-v3.Q4_K_M.gguf b/SageLlama-3.1-8B-v3.Q4_K_M.gguf new file mode 100644 index 0000000..c8e0651 --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715dff8c0cc74f985b7a425dd3ea4cea051e82f433fb30f4db0d8d592bcf4026 +size 4920735328 diff --git a/SageLlama-3.1-8B-v3.Q4_K_S.gguf b/SageLlama-3.1-8B-v3.Q4_K_S.gguf new file mode 100644 index 0000000..fc68b8d --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b5236bce56632f1a2e7773c3f94f6c38ec7e090b71077b243b85cae498b406 +size 4692670048 diff --git a/SageLlama-3.1-8B-v3.Q5_K_M.gguf b/SageLlama-3.1-8B-v3.Q5_K_M.gguf new file mode 100644 index 0000000..1a662ca --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477d7e0a75f2c28fc55cb9e7ef40ac25362480e7d604bd3192a94d508c2272ae +size 5732988512 diff --git a/SageLlama-3.1-8B-v3.Q5_K_S.gguf b/SageLlama-3.1-8B-v3.Q5_K_S.gguf new file mode 100644 index 0000000..5320eae --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97dcccdb28de2c3466e137f4469236b42f3aa04dc9d5e799caaaca77abe73841 +size 5599295072 diff --git a/SageLlama-3.1-8B-v3.Q6_K.gguf b/SageLlama-3.1-8B-v3.Q6_K.gguf new file mode 100644 index 0000000..2c889a1 --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72925103bf6fab6541cd67abd65de92eae9c46742676a6efd8e03fabd743cf08 +size 6596007520 diff --git a/SageLlama-3.1-8B-v3.Q8_0.gguf b/SageLlama-3.1-8B-v3.Q8_0.gguf new file mode 100644 index 0000000..aec6afe --- /dev/null +++ b/SageLlama-3.1-8B-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7cf45ed9a2bf3ce59c740bcb3a2c5a6d883cae59eb1b5e0f232f54a78422c87 +size 8540771936 diff --git a/SageLlama-3.1-8B-v3.f16.gguf b/SageLlama-3.1-8B-v3.f16.gguf new file mode 100644 index 0000000..257a5ba --- /dev/null +++ b/SageLlama-3.1-8B-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85bb58b06443fe05d5ad5ca49133ee6fbd58340e8daa67dcda43aafb30ed8c97 +size 16068892256