commit 960698cefe7815828b261773d80d3029c07f1efc Author: ModelHub XC Date: Fri Oct 2 20:49:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/shisa-v2.1-qwen3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40b7a6a --- /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 +shisa-v2.1-qwen3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2.1-qwen3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3b90a15 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: shisa-ai/shisa-v2.1-qwen3-8b +datasets: +- shisa-ai/shisa-v2.1-sharegpt +language: +- ja +- en +library_name: transformers +license: apache-2.0 +model_name: Llama 3.2 Shisa V2.1 3B +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- shisa +- qwen +- axolotl +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/shisa-ai/shisa-v2.1-qwen3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#shisa-v2.1-qwen3-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-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/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2.1-qwen3-8b-GGUF/resolve/main/shisa-v2.1-qwen3-8b.f16.gguf) | f16 | 16.5 | 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/shisa-v2.1-qwen3-8b.IQ4_XS.gguf b/shisa-v2.1-qwen3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..b4dd713 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d7a87e413e56b664d78ae3ff180a657d9932d009df8fd049feea23119b26ac +size 4593297440 diff --git a/shisa-v2.1-qwen3-8b.Q2_K.gguf b/shisa-v2.1-qwen3-8b.Q2_K.gguf new file mode 100644 index 0000000..3bcf661 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f592bad4b2baab17b5393594a7c3a8ad29a2152c11a872624ec3c2b595395bdd +size 3281733664 diff --git a/shisa-v2.1-qwen3-8b.Q3_K_L.gguf b/shisa-v2.1-qwen3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..4425468 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711277e227a2e43545cc989069f8509befd4aee87313a4e28646981efbac1335 +size 4431394848 diff --git a/shisa-v2.1-qwen3-8b.Q3_K_M.gguf b/shisa-v2.1-qwen3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..b0b3d8d --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf267593c08dc12f86015b94b6f3f071299d3f485dd7a2afcad916aa26b1363 +size 4124162080 diff --git a/shisa-v2.1-qwen3-8b.Q3_K_S.gguf b/shisa-v2.1-qwen3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..2d9637b --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2a4a28ed50391cefad7b30b6ab9b2356a27df5d500c84bf1b8164fbac15b48d +size 3769612320 diff --git a/shisa-v2.1-qwen3-8b.Q4_K_M.gguf b/shisa-v2.1-qwen3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..57509d3 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d042f108a86d266bb8ed89b37cbad73dcf6d40abb624272eab062eb61114069e +size 5027784736 diff --git a/shisa-v2.1-qwen3-8b.Q4_K_S.gguf b/shisa-v2.1-qwen3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..b7d6f5f --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d0d20626d3cacbb00666a69702e79157b1c928f65ff3b0c51e5f691cc6ae55 +size 4802013216 diff --git a/shisa-v2.1-qwen3-8b.Q5_K_M.gguf b/shisa-v2.1-qwen3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..5d14c56 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03c028b966e9d5f65b774cf90709237e82faa1072e70bf14ba44ca6ab5e79608 +size 5851113504 diff --git a/shisa-v2.1-qwen3-8b.Q5_K_S.gguf b/shisa-v2.1-qwen3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..9625bb0 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:575c9677e94192811371a2ecc47c4aca79e5314038a0cf1c1118629fce9c200c +size 5720762400 diff --git a/shisa-v2.1-qwen3-8b.Q6_K.gguf b/shisa-v2.1-qwen3-8b.Q6_K.gguf new file mode 100644 index 0000000..e619770 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4674d09bfb03da08b38fa6909a407372c8648ae3e075fcd3d18d66122afc9cee +size 6725900320 diff --git a/shisa-v2.1-qwen3-8b.Q8_0.gguf b/shisa-v2.1-qwen3-8b.Q8_0.gguf new file mode 100644 index 0000000..e50d205 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b155876d2d8a3554a04e4896a345ec7a19f32539fda0305a04ccd20211022d82 +size 8709519392 diff --git a/shisa-v2.1-qwen3-8b.f16.gguf b/shisa-v2.1-qwen3-8b.f16.gguf new file mode 100644 index 0000000..f60f3e4 --- /dev/null +++ b/shisa-v2.1-qwen3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5555cfd10b7fde8710c4d97d5fd7a4f2e8cada3d39a0d859af6a6e2b94c3b74b +size 16388044832