commit 792624c9b98af18d340693daddf49cc613e6b554 Author: ModelHub XC Date: Sun Jun 14 02:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Magnum-3b-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..203b410 --- /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 +Magnum-3b-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Magnum-3b-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Magnum-3b-v1.IQ4_XS.gguf b/Magnum-3b-v1.IQ4_XS.gguf new file mode 100644 index 0000000..60a96b3 --- /dev/null +++ b/Magnum-3b-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e52e182a29c70f2190f799f55c7047c88101cad2dad0e3632d4890c1e8abbef +size 1840903264 diff --git a/Magnum-3b-v1.Q2_K.gguf b/Magnum-3b-v1.Q2_K.gguf new file mode 100644 index 0000000..a4ccd4a --- /dev/null +++ b/Magnum-3b-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959cb71e250b0b16320adf814581ef57a8aed1ded144de601cd7df65551be951 +size 1363932256 diff --git a/Magnum-3b-v1.Q3_K_L.gguf b/Magnum-3b-v1.Q3_K_L.gguf new file mode 100644 index 0000000..c29ab74 --- /dev/null +++ b/Magnum-3b-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c43718db6309146197322e37d3d382b018179d18c5b032e414c5e5a6829503 +size 1815344224 diff --git a/Magnum-3b-v1.Q3_K_M.gguf b/Magnum-3b-v1.Q3_K_M.gguf new file mode 100644 index 0000000..ccc07b1 --- /dev/null +++ b/Magnum-3b-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcba1a83d9fe5e8c77dd03ca5e0125cae1c3c5fa46cd437cc58b0d3570f8ea32 +size 1687155808 diff --git a/Magnum-3b-v1.Q3_K_S.gguf b/Magnum-3b-v1.Q3_K_S.gguf new file mode 100644 index 0000000..265a5b0 --- /dev/null +++ b/Magnum-3b-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf55332965e9687b0c861d2fbcfe243e6e1e24028c246d1f9bc1fe347c7a8c78 +size 1542845536 diff --git a/Magnum-3b-v1.Q4_K_M.gguf b/Magnum-3b-v1.Q4_K_M.gguf new file mode 100644 index 0000000..f7a0bc9 --- /dev/null +++ b/Magnum-3b-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94f89fc5188d3f91e507e0a66b6af01cdab5b360baf4cf7ac8874553205c3e5 +size 2019374176 diff --git a/Magnum-3b-v1.Q4_K_S.gguf b/Magnum-3b-v1.Q4_K_S.gguf new file mode 100644 index 0000000..3130570 --- /dev/null +++ b/Magnum-3b-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11516de5a37ea7ae86beafa61d8f206cabc19c9b89267567592328a7eca5af2f +size 1928197216 diff --git a/Magnum-3b-v1.Q5_K_M.gguf b/Magnum-3b-v1.Q5_K_M.gguf new file mode 100644 index 0000000..24d470f --- /dev/null +++ b/Magnum-3b-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5231aabc799f12ed80ad1c33dd262c514f2cd788dd45039b47417643288115df +size 2322150496 diff --git a/Magnum-3b-v1.Q5_K_S.gguf b/Magnum-3b-v1.Q5_K_S.gguf new file mode 100644 index 0000000..e72d3ae --- /dev/null +++ b/Magnum-3b-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31c5b95e4af89476c7ee0e027a8aad38701febcaeab5e2e29639afaf8181405 +size 2269508704 diff --git a/Magnum-3b-v1.Q6_K.gguf b/Magnum-3b-v1.Q6_K.gguf new file mode 100644 index 0000000..2bbde0b --- /dev/null +++ b/Magnum-3b-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b861d450eb247e1786a98251f8ab45e9efd2a47125bcf0b3516326ee07305e2e +size 2643850336 diff --git a/Magnum-3b-v1.Q8_0.gguf b/Magnum-3b-v1.Q8_0.gguf new file mode 100644 index 0000000..976a5f4 --- /dev/null +++ b/Magnum-3b-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cd365d49823179adade64062ddab6a00d7df71c5904c5b5d35c2f0f4bb554f +size 3421895776 diff --git a/Magnum-3b-v1.f16.gguf b/Magnum-3b-v1.f16.gguf new file mode 100644 index 0000000..f21ff71 --- /dev/null +++ b/Magnum-3b-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7009855e644a76982972b79f8c9603205330d6b10ab4e9cd23adb64a4861c283 +size 6433684576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..176e83c --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: UUFO-Aigis/Magnum-3b-v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/UUFO-Aigis/Magnum-3b-v1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Magnum-3b-v1-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/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Magnum-3b-v1-GGUF/resolve/main/Magnum-3b-v1.f16.gguf) | f16 | 6.5 | 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. + +