commit 5f7a04c457d8d213c9d264019bf7fa1f63ddb5a5 Author: ModelHub XC Date: Thu Jun 4 20:54:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QAi-1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c15a3d --- /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-1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QAi-1.1.IQ4_XS.gguf b/QAi-1.1.IQ4_XS.gguf new file mode 100644 index 0000000..97d1386 --- /dev/null +++ b/QAi-1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87d4e49a515ecafbe6b5d0f09b2c299fff5986512d1d58d52a31b211d964e88 +size 1753185568 diff --git a/QAi-1.1.Q2_K.gguf b/QAi-1.1.Q2_K.gguf new file mode 100644 index 0000000..05050f3 --- /dev/null +++ b/QAi-1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4596e0e17cbfedcd06a28ecd06d3ffecce697fbb75683c26f25b7db306230f +size 1274756384 diff --git a/QAi-1.1.Q3_K_L.gguf b/QAi-1.1.Q3_K_L.gguf new file mode 100644 index 0000000..1f6f639 --- /dev/null +++ b/QAi-1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539f957aaa0f86c84c9664c65a203a39846455cdba9915ecabd8483d3b2e6510 +size 1707392288 diff --git a/QAi-1.1.Q3_K_M.gguf b/QAi-1.1.Q3_K_M.gguf new file mode 100644 index 0000000..93f0d1a --- /dev/null +++ b/QAi-1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d7d8427201181a5d5253712d1309f63bae68fc5227a69ebc53b8cea2844d7b +size 1590476064 diff --git a/QAi-1.1.Q3_K_S.gguf b/QAi-1.1.Q3_K_S.gguf new file mode 100644 index 0000000..03af954 --- /dev/null +++ b/QAi-1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65eafc281c11d7c783f865f7785b1620604c8c8faed317e9607a89155c457bfc +size 1454357792 diff --git a/QAi-1.1.Q4_K_M.gguf b/QAi-1.1.Q4_K_M.gguf new file mode 100644 index 0000000..100829a --- /dev/null +++ b/QAi-1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56be3bc2b1368d7a92a4feb39266ef51847c33504331c87ddc71c5277433f48e +size 1929903392 diff --git a/QAi-1.1.Q4_K_S.gguf b/QAi-1.1.Q4_K_S.gguf new file mode 100644 index 0000000..3a5ab1d --- /dev/null +++ b/QAi-1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf485d957d552bb744b7d10da3a9b07d47081247b8bbd8c999200f9c09bf4b87 +size 1834384672 diff --git a/QAi-1.1.Q5_K_M.gguf b/QAi-1.1.Q5_K_M.gguf new file mode 100644 index 0000000..11ebfd1 --- /dev/null +++ b/QAi-1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a9e239b87791f1533f194839581308aea33cd6c003c212401c43ce7facb792 +size 2224815392 diff --git a/QAi-1.1.Q5_K_S.gguf b/QAi-1.1.Q5_K_S.gguf new file mode 100644 index 0000000..4ed2d17 --- /dev/null +++ b/QAi-1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf47441d491175df1b1f83480ab37e2de04b3802736341714b68b56adc1e7d4 +size 2169666848 diff --git a/QAi-1.1.Q6_K.gguf b/QAi-1.1.Q6_K.gguf new file mode 100644 index 0000000..f46f45e --- /dev/null +++ b/QAi-1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38bbb9579f1fc826cf0e92ff7d219f1facb94080828d399011a2ed2b29bf853b +size 2538159392 diff --git a/QAi-1.1.Q8_0.gguf b/QAi-1.1.Q8_0.gguf new file mode 100644 index 0000000..072d077 --- /dev/null +++ b/QAi-1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f49c161f21cd070b07dfe65903a5cca2773dba1164e8cdfe8d5ae6e70aed29 +size 3285476640 diff --git a/QAi-1.1.f16.gguf b/QAi-1.1.f16.gguf new file mode 100644 index 0000000..74b421d --- /dev/null +++ b/QAi-1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64cc5344aa5af3adf9d0090103c694e9a07a2df930f8b40a5c84e95c4c416ff3 +size 6178317600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a26f8a3 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: QwexGP/QAi-1.1 +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-1.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QAi-1.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QAi-1.1-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-1.1-GGUF/resolve/main/QAi-1.1.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-GGUF/resolve/main/QAi-1.1.f16.gguf) | f16 | 6.3 | 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. + +