commit f4fd4151dd5e28cd396e90965d80954e28112827 Author: ModelHub XC Date: Wed Jun 3 22:33:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NekoQA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5334732 --- /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 +NekoQA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NekoQA.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NekoQA.IQ4_XS.gguf b/NekoQA.IQ4_XS.gguf new file mode 100644 index 0000000..89393ed --- /dev/null +++ b/NekoQA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5137324f452e4bff7fa900aa60d2b1fb21624e7f5aa8c005af012aa9f5dfcc24 +size 369274496 diff --git a/NekoQA.Q2_K.gguf b/NekoQA.Q2_K.gguf new file mode 100644 index 0000000..4241f3c --- /dev/null +++ b/NekoQA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4ed78d7c13961dd2fdab8f1c448f5464301e7eec0e54af0e9ed88751b6ad35 +size 296234624 diff --git a/NekoQA.Q3_K_L.gguf b/NekoQA.Q3_K_L.gguf new file mode 100644 index 0000000..1900356 --- /dev/null +++ b/NekoQA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638520350116f03ee1610730331562a98d3e334e8abaa37cb5ffaaf836d39e70 +size 368488064 diff --git a/NekoQA.Q3_K_M.gguf b/NekoQA.Q3_K_M.gguf new file mode 100644 index 0000000..f37f74a --- /dev/null +++ b/NekoQA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d2953f5ddf343351cb6025a7bb37240bfab360db7727239d133ce39ead345a +size 347123328 diff --git a/NekoQA.Q3_K_S.gguf b/NekoQA.Q3_K_S.gguf new file mode 100644 index 0000000..6796e41 --- /dev/null +++ b/NekoQA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae65dcbcd5bc12e613aae154084acacc658278ea6da900b645602b27e59a365 +size 323071616 diff --git a/NekoQA.Q4_K_M.gguf b/NekoQA.Q4_K_M.gguf new file mode 100644 index 0000000..218dda7 --- /dev/null +++ b/NekoQA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b567d8ae226ed802220dcbf0c0a4b409a17140e3257adef3fb63787d07b096 +size 396701312 diff --git a/NekoQA.Q4_K_S.gguf b/NekoQA.Q4_K_S.gguf new file mode 100644 index 0000000..2eb5ae5 --- /dev/null +++ b/NekoQA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec8753c16138dc3dc454682f791ea5bd4f7f0243f2fc70aa1181c46a7eff309 +size 383266432 diff --git a/NekoQA.Q5_K_M.gguf b/NekoQA.Q5_K_M.gguf new file mode 100644 index 0000000..a2dd1a5 --- /dev/null +++ b/NekoQA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21381c450ebb1f2e487ae71488b369e19cb43954d3cda853c00195a2911b130 +size 444411520 diff --git a/NekoQA.Q5_K_S.gguf b/NekoQA.Q5_K_S.gguf new file mode 100644 index 0000000..679763c --- /dev/null +++ b/NekoQA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:479ed413f180d32c36aa6fb2acc172c9ebe6cd307633cf93d5275a8099e0a2e8 +size 436612736 diff --git a/NekoQA.Q6_K.gguf b/NekoQA.Q6_K.gguf new file mode 100644 index 0000000..771eb85 --- /dev/null +++ b/NekoQA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ceb2683f7fba4fad6e727086889676848b75996410c159c5d53ced175c6263e +size 495103616 diff --git a/NekoQA.Q8_0.gguf b/NekoQA.Q8_0.gguf new file mode 100644 index 0000000..63aa855 --- /dev/null +++ b/NekoQA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a857972043c4819eefbb0bb150a7dad13248ac528faae23b1b73a5fcbf6291 +size 639443584 diff --git a/NekoQA.f16.gguf b/NekoQA.f16.gguf new file mode 100644 index 0000000..b980d14 --- /dev/null +++ b/NekoQA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a19ded0a75c318ba8e8602c320d20abe3953cac76155abdda048b2c86980f1 +size 1198178944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4789118 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: koishi831/NekoQA +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/koishi831/NekoQA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NekoQA-GGUF).*** + +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/NekoQA-GGUF/resolve/main/NekoQA.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NekoQA-GGUF/resolve/main/NekoQA.f16.gguf) | f16 | 1.3 | 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. + +