commit 2bd533eab24f0484a4c75c8332a5a4d207f24adb Author: ModelHub XC Date: Sat Oct 24 08:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b3ed5af --- /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 +Wisenut-3.1-8B-IC-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wisenut-3.1-8B-IC-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0d7a0c4 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: wisenut-nlp-team/Wisenut-LLaMA-3.1-8B-IC-SFT +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/wisenut-nlp-team/Wisenut-LLaMA-3.1-8B-IC-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-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/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Wisenut-3.1-8B-IC-SFT-GGUF/resolve/main/Wisenut-3.1-8B-IC-SFT.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/Wisenut-3.1-8B-IC-SFT.IQ4_XS.gguf b/Wisenut-3.1-8B-IC-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..2c50ea8 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8594d991f0d8529f659d1def729b548a2abadf797e53c9fdf6d922bb227dca9 +size 4484364032 diff --git a/Wisenut-3.1-8B-IC-SFT.Q2_K.gguf b/Wisenut-3.1-8B-IC-SFT.Q2_K.gguf new file mode 100644 index 0000000..9c80936 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb5980ea163672d2ce770e58fb86900f953b825e0380ed1deb5891399fbe2a7 +size 3179132672 diff --git a/Wisenut-3.1-8B-IC-SFT.Q3_K_L.gguf b/Wisenut-3.1-8B-IC-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..9ac7c42 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9faf3124bce844e1ecd8d722502c5bc303c3c6a60b091c9cfafba6fbcf0745 +size 4321957632 diff --git a/Wisenut-3.1-8B-IC-SFT.Q3_K_M.gguf b/Wisenut-3.1-8B-IC-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..dc1f94d --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1784110a685ec4f71eb28f23768439bbd42dca350aa3bfb5a8087612d73b65c0 +size 4018919168 diff --git a/Wisenut-3.1-8B-IC-SFT.Q3_K_S.gguf b/Wisenut-3.1-8B-IC-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..af81eb7 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ea83c7605183ed17984ab382417752872fcd1e54afc26f781342fe67e43ed3 +size 3664500480 diff --git a/Wisenut-3.1-8B-IC-SFT.Q4_K_M.gguf b/Wisenut-3.1-8B-IC-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..095e258 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:047e54d8e4ca1fc671cea3a02db5a8b3bc358a4da06506d5530a77e5be93edaa +size 4920735488 diff --git a/Wisenut-3.1-8B-IC-SFT.Q4_K_S.gguf b/Wisenut-3.1-8B-IC-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..9207077 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ad79fc95b39b7ad3e80e8353a32703c3fe7edaef1119eb9798f4c5859c6b52 +size 4692670208 diff --git a/Wisenut-3.1-8B-IC-SFT.Q5_K_M.gguf b/Wisenut-3.1-8B-IC-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..bd613dc --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899f539a2144c49f4d2c64a073d68f71aa8d096b9afb7caf5a622ff83738d135 +size 5732988672 diff --git a/Wisenut-3.1-8B-IC-SFT.Q5_K_S.gguf b/Wisenut-3.1-8B-IC-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..18851ad --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3dc96a36d8649a6fb78e22128bca82d83455808df6b8377219dbfcf691bb472 +size 5599295232 diff --git a/Wisenut-3.1-8B-IC-SFT.Q6_K.gguf b/Wisenut-3.1-8B-IC-SFT.Q6_K.gguf new file mode 100644 index 0000000..8d854ac --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8540a0ddf2dd53926d002bb779a3358e321511ff0fc3a9976e50faa4de24b386 +size 6596007680 diff --git a/Wisenut-3.1-8B-IC-SFT.Q8_0.gguf b/Wisenut-3.1-8B-IC-SFT.Q8_0.gguf new file mode 100644 index 0000000..6ae2e26 --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4faed25c1536152331762c9ad0a26512f6661f7bf71d0c17036867728768f1d +size 8540772096 diff --git a/Wisenut-3.1-8B-IC-SFT.f16.gguf b/Wisenut-3.1-8B-IC-SFT.f16.gguf new file mode 100644 index 0000000..f1b13fc --- /dev/null +++ b/Wisenut-3.1-8B-IC-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5d2b5a850ed81541423c37fab908cc32da16ea0ec2c15af76c8535510d09a2 +size 16068892416