commit 24db07b98b0b9375e7d1841affa66048a28b9db7 Author: ModelHub XC Date: Thu Jun 4 21:56:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QAi-2.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dcc36b0 --- /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 +QAi-2.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QAi-2.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QAi-2.0.IQ4_XS.gguf b/QAi-2.0.IQ4_XS.gguf new file mode 100644 index 0000000..f91aa21 --- /dev/null +++ b/QAi-2.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7c14e91bc200f349680d1d9e5175bba428c58ee5167894d4e7ed99c439e83e +size 902183328 diff --git a/QAi-2.0.Q2_K.gguf b/QAi-2.0.Q2_K.gguf new file mode 100644 index 0000000..9aad1d3 --- /dev/null +++ b/QAi-2.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec322352e74dee54d6cc51224d2d5004d76908b69d4669adebc8e4a97cf5da86 +size 676305312 diff --git a/QAi-2.0.Q3_K_L.gguf b/QAi-2.0.Q3_K_L.gguf new file mode 100644 index 0000000..f688ddb --- /dev/null +++ b/QAi-2.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11063d092d44116db04ed894ccaaec8616e5fc25cb1c65e63ad353694fd4760b +size 880163232 diff --git a/QAi-2.0.Q3_K_M.gguf b/QAi-2.0.Q3_K_M.gguf new file mode 100644 index 0000000..fd9a512 --- /dev/null +++ b/QAi-2.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4791597660a423da1e19211e07bb66a8b5bdf7a03679b7aac4bd55095dd039f0 +size 824179104 diff --git a/QAi-2.0.Q3_K_S.gguf b/QAi-2.0.Q3_K_S.gguf new file mode 100644 index 0000000..e151201 --- /dev/null +++ b/QAi-2.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96a0bf0d29f67d6615f54941feb9b30ee4f964e74dfb0b323940606bef186ad +size 760945056 diff --git a/QAi-2.0.Q4_K_M.gguf b/QAi-2.0.Q4_K_M.gguf new file mode 100644 index 0000000..95b7519 --- /dev/null +++ b/QAi-2.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798ca32ddaac4ba1389a42c00db5769bae39bf474016c2d040b0604d76db8497 +size 986048928 diff --git a/QAi-2.0.Q4_K_S.gguf b/QAi-2.0.Q4_K_S.gguf new file mode 100644 index 0000000..42fb087 --- /dev/null +++ b/QAi-2.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f518cccf893aaa366f688e87e4e543326c858cd86525ad6f9590207c9352ee7a +size 940312992 diff --git a/QAi-2.0.Q5_K_M.gguf b/QAi-2.0.Q5_K_M.gguf new file mode 100644 index 0000000..8a468bd --- /dev/null +++ b/QAi-2.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac89320336b89646b316b18a71a00e5be188341daeaeefd391ccdbb3620739e +size 1125050784 diff --git a/QAi-2.0.Q5_K_S.gguf b/QAi-2.0.Q5_K_S.gguf new file mode 100644 index 0000000..9a0c527 --- /dev/null +++ b/QAi-2.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1034bd1bcbe2a904561bff9ca5af9428d804983de9891215e7c318279033eee0 +size 1098729888 diff --git a/QAi-2.0.Q6_K.gguf b/QAi-2.0.Q6_K.gguf new file mode 100644 index 0000000..6a21b3a --- /dev/null +++ b/QAi-2.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e032202b4f32468595330e64ff25372f42bd1e478a45cbc8fa70bac75f8ebff +size 1272740256 diff --git a/QAi-2.0.Q8_0.gguf b/QAi-2.0.Q8_0.gguf new file mode 100644 index 0000000..381b3ee --- /dev/null +++ b/QAi-2.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c589cae3730403c76a9d64337ab62a400383a1044a6dd1fd9f443b0674ecc339 +size 1646573472 diff --git a/QAi-2.0.f16.gguf b/QAi-2.0.f16.gguf new file mode 100644 index 0000000..ddf5729 --- /dev/null +++ b/QAi-2.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5504c6d2423121b2ac64bd470cb905459499fda68f744945709ad3d99146dbbc +size 3093669792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..84acc28 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: QwexGP/QAi-2.0 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/QwexGP/QAi-2.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QAi-2.0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QAi-2.0-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/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-2.0-GGUF/resolve/main/QAi-2.0.f16.gguf) | f16 | 3.2 | 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. + +