commit 3f9c9c1a6c9b3a849802d4440f1a6e538192276c Author: ModelHub XC Date: Sat Apr 11 06:28:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/An4-7Bv3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..62fa103 --- /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 +An4-7Bv3.f16.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +An4-7Bv3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/An4-7Bv3.IQ4_XS.gguf b/An4-7Bv3.IQ4_XS.gguf new file mode 100644 index 0000000..0c3a79c --- /dev/null +++ b/An4-7Bv3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15f75d054836c84ea1f0cbaec614103930d02f9e8cad56114d9d6582b1ceeb4 +size 3944390048 diff --git a/An4-7Bv3.Q2_K.gguf b/An4-7Bv3.Q2_K.gguf new file mode 100644 index 0000000..28cf5b2 --- /dev/null +++ b/An4-7Bv3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323c2cf34e08830122d56b1ec7af8c56c57ac174939f5862f188af77417fda48 +size 2719243680 diff --git a/An4-7Bv3.Q3_K_L.gguf b/An4-7Bv3.Q3_K_L.gguf new file mode 100644 index 0000000..0d2cd52 --- /dev/null +++ b/An4-7Bv3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d25ebea6c382516e0b958c23a611604cb5062d98de56a5a4535586d90957c7c +size 3822026144 diff --git a/An4-7Bv3.Q3_K_M.gguf b/An4-7Bv3.Q3_K_M.gguf new file mode 100644 index 0000000..054c552 --- /dev/null +++ b/An4-7Bv3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cee4e7729cfa224a6699921560ef796335349861ea8206b729ad615205fdf57 +size 3518987680 diff --git a/An4-7Bv3.Q3_K_S.gguf b/An4-7Bv3.Q3_K_S.gguf new file mode 100644 index 0000000..7a60bd7 --- /dev/null +++ b/An4-7Bv3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e69102cb9ddadd703880495ca76b1516df5a4c68bba019928d7e9a17f3eca60 +size 3164568992 diff --git a/An4-7Bv3.Q4_K_M.gguf b/An4-7Bv3.Q4_K_M.gguf new file mode 100644 index 0000000..1b78954 --- /dev/null +++ b/An4-7Bv3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a74b54d121b2179c6b6564cb6c9ca2aa8946e567ea5536ccfd05ad0d8d06c25 +size 4368440736 diff --git a/An4-7Bv3.Q4_K_S.gguf b/An4-7Bv3.Q4_K_S.gguf new file mode 100644 index 0000000..af006c0 --- /dev/null +++ b/An4-7Bv3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1b5194437b23ca19118b8cc4d0d2a93d321b1f1f4a9a24135237317de267ac +size 4140375456 diff --git a/An4-7Bv3.Q5_K_M.gguf b/An4-7Bv3.Q5_K_M.gguf new file mode 100644 index 0000000..33fd838 --- /dev/null +++ b/An4-7Bv3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8a1543679fcee79f287f8feb6535fd751cdd5fed5aa0031641af18d3d4b553 +size 5131410848 diff --git a/An4-7Bv3.Q5_K_S.gguf b/An4-7Bv3.Q5_K_S.gguf new file mode 100644 index 0000000..9f1fdaf --- /dev/null +++ b/An4-7Bv3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf2d983b17f6a7e860dec708066c44c2677be6215584b05180b55879bdc76370 +size 4997717408 diff --git a/An4-7Bv3.Q6_K.gguf b/An4-7Bv3.Q6_K.gguf new file mode 100644 index 0000000..c3f78d9 --- /dev/null +++ b/An4-7Bv3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3152b163188a8afd7d16343393d6fc239fb78aadc66d4c36d6607326db7e97 +size 5942066592 diff --git a/An4-7Bv3.Q8_0.gguf b/An4-7Bv3.Q8_0.gguf new file mode 100644 index 0000000..af24e70 --- /dev/null +++ b/An4-7Bv3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db1cd07100d14c225b59419faacc8706c9b456a5a284f1122861686ff41c0b9 +size 7695859104 diff --git a/An4-7Bv3.f16.gguf b/An4-7Bv3.f16.gguf new file mode 100644 index 0000000..0a3055f --- /dev/null +++ b/An4-7Bv3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb33f2907762062ed29f6c1a98c8e7fdce2518e41482a673c254233979190e0f +size 14484733344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..77f452e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Smuggling1710/An4-7Bv3 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Nitral-AI/Kunocchini-7b-128k-test +- Smuggling1710/An4-7Bv2 +- Endevor/InfinityRP-v1-7B +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/Smuggling1710/An4-7Bv3 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/An4-7Bv3-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/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/An4-7Bv3-GGUF/resolve/main/An4-7Bv3.f16.gguf) | f16 | 14.6 | 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. + +