commit a0594997de620a30e450a2bde3950556cbeca858 Author: ModelHub XC Date: Wed Jun 3 04:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f927069 --- /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 +ExpertWeaver-7B-E64-A14-S2-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ExpertWeaver-7B-E64-A14-S2-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.IQ4_XS.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2f46af5 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de45b5c93735be8f1fc58b387ce7f6a583b1ed095729b81ec80fd94cee71e013 +size 4256645728 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q2_K.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q2_K.gguf new file mode 100644 index 0000000..aa1ab7b --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f268667f0dd9c6428dc06f34421f464c3f6d266ccbdaaddb4297281ce0f8fc6 +size 3230904928 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_L.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6e196f9 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249f8e2b1bb88fa01fb5a770da329b16b042a01701dc3620fee6809acbb3879c +size 4149684832 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_M.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..5a48165 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d62e15702dad0d05307769eb6e4e221412a34cd1c2dfd71ff7a5b0d9941be5 +size 3987286624 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_S.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b3fe930 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e380538ef02d8fde04426df37a3f29d6f47abeeec4c0c0646250dd87db18cc1b +size 3696896608 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_M.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..4f2b666 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d186a4949f9dea966eb2d25e5fb228b8b09fb7171169c8acb0098be6543b5f6 +size 4954436192 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_S.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..33eb4b3 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb2085dabc1e4bd514faf096ce5238d30604dbe28074f391631f051d1a793ef +size 4614300256 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_M.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..61ec302 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72da22a05f721e6ad148711dc42821d5e75a6199a24ee92747221fe8cf4d224 +size 5642334816 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_S.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..e2e5a22 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded09ca7a14fdde378c8066ae9c26a6e1a0bb95b07faa9a4bdfc68347055ba83 +size 5349909088 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q6_K.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q6_K.gguf new file mode 100644 index 0000000..d879684 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9397598cad2e0551c465eeae3b227d91e486244bc596f1af6a514e702799d4 +size 6600825440 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.Q8_0.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.Q8_0.gguf new file mode 100644 index 0000000..c64cae4 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a669fa7555e23a0f923acffaba55a89317e0c02f9c54050001e819d1e971e231 +size 7959849568 diff --git a/ExpertWeaver-7B-E64-A14-S2-instruct.f16.gguf b/ExpertWeaver-7B-E64-A14-S2-instruct.f16.gguf new file mode 100644 index 0000000..6408361 --- /dev/null +++ b/ExpertWeaver-7B-E64-A14-S2-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d5730e185aa31d2b280a9bded266429a69dc3aeb0ca8e0b7abffbb456ebb6d +size 14954670688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3cfc7bb --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Styxxxx/ExpertWeaver-7B-E64-A14-S2-instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Styxxxx/ExpertWeaver-7B-E64-A14-S2-instruct + + +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/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q5_K_M.gguf) | Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ExpertWeaver-7B-E64-A14-S2-instruct-GGUF/resolve/main/ExpertWeaver-7B-E64-A14-S2-instruct.f16.gguf) | f16 | 15.1 | 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. + +