commit acbe36321d59e9e133be2daa2a9e5012f320e6b9 Author: ModelHub XC Date: Sun Sep 27 01:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SageLlama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d7fdff --- /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.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SageLlama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..98be9a8 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: pascarujo/SageLlama-3.1-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +--- +## About + + + + + + +static quants of https://huggingface.co/pascarujo/SageLlama-3.1-8B + + +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/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SageLlama-3.1-8B-GGUF/resolve/main/SageLlama-3.1-8B.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.IQ3_M.gguf b/SageLlama-3.1-8B.IQ3_M.gguf new file mode 100644 index 0000000..3e1f406 --- /dev/null +++ b/SageLlama-3.1-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7ab91577a017b1a3ee98df546125141f17f1a755b17788b5f7968205e2b11f +size 3784823552 diff --git a/SageLlama-3.1-8B.IQ3_S.gguf b/SageLlama-3.1-8B.IQ3_S.gguf new file mode 100644 index 0000000..33a62ba --- /dev/null +++ b/SageLlama-3.1-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32150f12313f99d4129ae82ea2aa58c4ad3ea7b10d028801d33d4b0a36892aa2 +size 3682325248 diff --git a/SageLlama-3.1-8B.IQ3_XS.gguf b/SageLlama-3.1-8B.IQ3_XS.gguf new file mode 100644 index 0000000..a86709b --- /dev/null +++ b/SageLlama-3.1-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ec9e2fb698c333cbdf6ae7271394607b4e2924f86b194d16d9f378e259a5a3 +size 3518747392 diff --git a/SageLlama-3.1-8B.IQ4_XS.gguf b/SageLlama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..71e7d5a --- /dev/null +++ b/SageLlama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d6d3d160c18476cc1641d0e812233ff3b11736061c31c87f5832b99bff104a +size 4484363008 diff --git a/SageLlama-3.1-8B.Q2_K.gguf b/SageLlama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..d30dac1 --- /dev/null +++ b/SageLlama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7c3ac51537d01614825fa52395372cecb5e74d5235bde9393d4690858259af +size 3179131648 diff --git a/SageLlama-3.1-8B.Q3_K_L.gguf b/SageLlama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..43f9659 --- /dev/null +++ b/SageLlama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18a0caecc801378675b57880f30d18982ee4dac1d30598f9a484404520cb8b8 +size 4321956608 diff --git a/SageLlama-3.1-8B.Q3_K_M.gguf b/SageLlama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..a088b9a --- /dev/null +++ b/SageLlama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54382a44e8603880e0f85646d24c8987231fd0ace64db639b99d02169cb0cd8a +size 4018918144 diff --git a/SageLlama-3.1-8B.Q3_K_S.gguf b/SageLlama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..e0d91a8 --- /dev/null +++ b/SageLlama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a17b09af0a9111e30093cc49141a57387494d84856cf45064ef2c25816999f +size 3664499456 diff --git a/SageLlama-3.1-8B.Q4_K_M.gguf b/SageLlama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..4100d62 --- /dev/null +++ b/SageLlama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b8d5785c01cf1bd247cd388b556cf5242e9c10b12147c5da776b654949f8fc2 +size 4920734464 diff --git a/SageLlama-3.1-8B.Q4_K_S.gguf b/SageLlama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..4a7545e --- /dev/null +++ b/SageLlama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf7accf08209d57bdc4a1c347c13baf566d93bfca77fedcdaf88e09d2f92204 +size 4692669184 diff --git a/SageLlama-3.1-8B.Q5_K_M.gguf b/SageLlama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..8e2de08 --- /dev/null +++ b/SageLlama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949c27326e81922d91c8287335c6829c6e5c2f5583bee8b73c1e3eee4b6df47e +size 5732987648 diff --git a/SageLlama-3.1-8B.Q5_K_S.gguf b/SageLlama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..3bdddc8 --- /dev/null +++ b/SageLlama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea18c628bf69db1337766513e140cb6f37ed080b5c89fb43fcc86769e6bb2f53 +size 5599294208 diff --git a/SageLlama-3.1-8B.Q6_K.gguf b/SageLlama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..de3cd2e --- /dev/null +++ b/SageLlama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97969e08b49534caa02d42d9bf059e198b96940be13d5b1060501ec06491de32 +size 6596006656 diff --git a/SageLlama-3.1-8B.Q8_0.gguf b/SageLlama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..ba778fb --- /dev/null +++ b/SageLlama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f8444b3d48109e79f05d91a5b732df9812150547dd4ceab8228aca0176125b +size 8540771072 diff --git a/SageLlama-3.1-8B.f16.gguf b/SageLlama-3.1-8B.f16.gguf new file mode 100644 index 0000000..326d8dd --- /dev/null +++ b/SageLlama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437bc5eccf92084038996c575db5eca5a9f9ff0cb4fff22ddb273cbbc69d36b8 +size 16068891392