commit 3607e6ec0d4c8b9b9ccff396f19a96c0a6f7fa9c Author: ModelHub XC Date: Sat May 9 12:47:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/INF-AZ-7B-0524-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..379a6c0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +INF-AZ-7B-0524.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.f16.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +INF-AZ-7B-0524.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/INF-AZ-7B-0524.IQ4_XS.gguf b/INF-AZ-7B-0524.IQ4_XS.gguf new file mode 100644 index 0000000..5ba6e1c --- /dev/null +++ b/INF-AZ-7B-0524.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0251f956295ea7853ec4dab721b48056dcde0f2628cf25d6a8a801fc413f42 +size 4250299168 diff --git a/INF-AZ-7B-0524.Q2_K.gguf b/INF-AZ-7B-0524.Q2_K.gguf new file mode 100644 index 0000000..a097ab5 --- /dev/null +++ b/INF-AZ-7B-0524.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032c7f44029a60ecf9012d4adadf00b70e11e9da185c2535c4ddfd27dc6b7223 +size 3015940896 diff --git a/INF-AZ-7B-0524.Q3_K_L.gguf b/INF-AZ-7B-0524.Q3_K_L.gguf new file mode 100644 index 0000000..4b17807 --- /dev/null +++ b/INF-AZ-7B-0524.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54ee7d3c59958d264a7117cce09b640de68f8e6c9bf3c7aed937b0bb985041c +size 4088460064 diff --git a/INF-AZ-7B-0524.Q3_K_M.gguf b/INF-AZ-7B-0524.Q3_K_M.gguf new file mode 100644 index 0000000..229211d --- /dev/null +++ b/INF-AZ-7B-0524.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43fd7127d8d9e8a5b998a82bf0feb3e021b34a9f4818bfcf20b7fd5938756867 +size 3808391968 diff --git a/INF-AZ-7B-0524.Q3_K_S.gguf b/INF-AZ-7B-0524.Q3_K_S.gguf new file mode 100644 index 0000000..df175b2 --- /dev/null +++ b/INF-AZ-7B-0524.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa23f49752e7be2c49b74383a795839172cbbf17feb006ea6af022a0934f3a2 +size 3492369184 diff --git a/INF-AZ-7B-0524.Q4_K_M.gguf b/INF-AZ-7B-0524.Q4_K_M.gguf new file mode 100644 index 0000000..4251177 --- /dev/null +++ b/INF-AZ-7B-0524.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba932f91f0a1c5b97e91a02fc49aea60c3ad969af43713d1a13281ab012df628 +size 4683074336 diff --git a/INF-AZ-7B-0524.Q4_K_S.gguf b/INF-AZ-7B-0524.Q4_K_S.gguf new file mode 100644 index 0000000..135ec32 --- /dev/null +++ b/INF-AZ-7B-0524.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92df70664a951bab31abd761196178e3c7fd570fd9aa2871a6725a2cc453b47f +size 4457769760 diff --git a/INF-AZ-7B-0524.Q5_K_M.gguf b/INF-AZ-7B-0524.Q5_K_M.gguf new file mode 100644 index 0000000..9ee0207 --- /dev/null +++ b/INF-AZ-7B-0524.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3dc2bc160a10f8a26d2daa39a9a07c643a0d7fcaaa66f5541a88282fd66714 +size 5444832032 diff --git a/INF-AZ-7B-0524.Q5_K_S.gguf b/INF-AZ-7B-0524.Q5_K_S.gguf new file mode 100644 index 0000000..4c90091 --- /dev/null +++ b/INF-AZ-7B-0524.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd30ab4e8565f71e2e050b10ed9b7eed6e7dfd1e4c31b98e75480c12e854d92e +size 5315177248 diff --git a/INF-AZ-7B-0524.Q6_K.gguf b/INF-AZ-7B-0524.Q6_K.gguf new file mode 100644 index 0000000..044ba70 --- /dev/null +++ b/INF-AZ-7B-0524.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174b4f30cdc14979527ed60f951ed3449dc12f2197e94890570855de4173fc5b +size 6254199584 diff --git a/INF-AZ-7B-0524.Q8_0.gguf b/INF-AZ-7B-0524.Q8_0.gguf new file mode 100644 index 0000000..a5aeab1 --- /dev/null +++ b/INF-AZ-7B-0524.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7b263f734918df3b2ea810d983a270c3eba71bcfb7572a45c64a049834d48f +size 8098525984 diff --git a/INF-AZ-7B-0524.f16.gguf b/INF-AZ-7B-0524.f16.gguf new file mode 100644 index 0000000..7ad0d6e --- /dev/null +++ b/INF-AZ-7B-0524.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8fae63fe0b59b27ab4f0c8c6dc4ba062a12154f6a22ab1120a36379aa222939 +size 15237853984 diff --git a/INF-AZ-7B-0524.mmproj-Q8_0.gguf b/INF-AZ-7B-0524.mmproj-Q8_0.gguf new file mode 100644 index 0000000..a5ade31 --- /dev/null +++ b/INF-AZ-7B-0524.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5888321b652b6c26daee35eea0265676658a8846749e2e61807a28d3d58ee57b +size 853120224 diff --git a/INF-AZ-7B-0524.mmproj-f16.gguf b/INF-AZ-7B-0524.mmproj-f16.gguf new file mode 100644 index 0000000..7db3a04 --- /dev/null +++ b/INF-AZ-7B-0524.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c90a2d38defc9c5a7c6ade50648e3e3e78d7530a5d988ce4926f0bae45ca37 +size 1354163424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2af6c4d --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: infly/INF-AZ-7B-0524 +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/infly/INF-AZ-7B-0524 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#INF-AZ-7B-0524-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/INF-AZ-7B-0524-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/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/INF-AZ-7B-0524-GGUF/resolve/main/INF-AZ-7B-0524.f16.gguf) | f16 | 15.3 | 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. + +