commit e8938fa8196563ef675eafd7e6c2486145e6f5a3 Author: ModelHub XC Date: Mon Jun 15 00:11:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/s1.1_Llama3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45759c9 --- /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 +s1.1_Llama3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +s1.1_Llama3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..55157f7 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: AugustJW/s1.1_Llama3.1-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AugustJW/s1.1_Llama3.1-8B + + +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/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/s1.1_Llama3.1-8B-GGUF/resolve/main/s1.1_Llama3.1-8B.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/s1.1_Llama3.1-8B.IQ4_XS.gguf b/s1.1_Llama3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..0dade99 --- /dev/null +++ b/s1.1_Llama3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df170a776946cf0d7e0074a57ff13ebda735252c559492ea80bde54cce234f2 +size 4484367808 diff --git a/s1.1_Llama3.1-8B.Q2_K.gguf b/s1.1_Llama3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..4e2422a --- /dev/null +++ b/s1.1_Llama3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44aa551d748d1c25df133d6f52cb3dfc9519595c2f8d53a6bba4e335ba9481f2 +size 3179136448 diff --git a/s1.1_Llama3.1-8B.Q3_K_L.gguf b/s1.1_Llama3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..f4feeb5 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:303b3c044acc0cc1860993f911e670d71bcd13daf97c32e8d39aebab301bd025 +size 4321961408 diff --git a/s1.1_Llama3.1-8B.Q3_K_M.gguf b/s1.1_Llama3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..ecb5a23 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79eecc49f2acd4a1374bd4a61d820e052a8c0f01e36a82649de6d329cbda1079 +size 4018922944 diff --git a/s1.1_Llama3.1-8B.Q3_K_S.gguf b/s1.1_Llama3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5575dc8 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712edaca79d1c0905491070e5cabf28a1579dc97add700c73f96723766240495 +size 3664504256 diff --git a/s1.1_Llama3.1-8B.Q4_K_M.gguf b/s1.1_Llama3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a7aa0f8 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11074740bb768e113fc42d87f167dea9ff331df9188103a33c09a32ddaf40385 +size 4920739264 diff --git a/s1.1_Llama3.1-8B.Q4_K_S.gguf b/s1.1_Llama3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..3c9c668 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7deb1ebb52ea5f04a13cc8e9c57e175e66b9a48ba0f04c0e1ec1bb338c71fe50 +size 4692673984 diff --git a/s1.1_Llama3.1-8B.Q5_K_M.gguf b/s1.1_Llama3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..9d45d45 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ac074e98d46ae85edb923426639d3a40a1d3d7bfdc1f47a3fc04fbc7eaa961 +size 5732992448 diff --git a/s1.1_Llama3.1-8B.Q5_K_S.gguf b/s1.1_Llama3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..2eaacf3 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d64ae94ba8777567302d5d9e9f1276d584ea1dc14c62da45688791ea72b8b51 +size 5599299008 diff --git a/s1.1_Llama3.1-8B.Q6_K.gguf b/s1.1_Llama3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..8485378 --- /dev/null +++ b/s1.1_Llama3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b2122f53855acf80c5a07e1d71fcbbd62dc3c686cc06ea46cd18fc50b09ade +size 6596011456 diff --git a/s1.1_Llama3.1-8B.Q8_0.gguf b/s1.1_Llama3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..4668c6b --- /dev/null +++ b/s1.1_Llama3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665c67271aa63515726103379b94bf9f2eaa26f74c6fb17a5de6a9d35454ebb4 +size 8540775872 diff --git a/s1.1_Llama3.1-8B.f16.gguf b/s1.1_Llama3.1-8B.f16.gguf new file mode 100644 index 0000000..17fa767 --- /dev/null +++ b/s1.1_Llama3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa8c32cd80e0503b163febef6ec85defaaea0be845af179df4b2b658360f559 +size 16068896192