commit bbe63a16998ed0465adb9157fb878fd967825673 Author: ModelHub XC Date: Mon Apr 27 13:46:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-3B-ShiningValiant2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..018c881 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama3.2-3B-ShiningValiant2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3B-ShiningValiant2.IQ4_XS.gguf b/Llama3.2-3B-ShiningValiant2.IQ4_XS.gguf new file mode 100644 index 0000000..39c38b9 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9cbb6657b7b4f2dab3c7b4ea87389277de31be5178f25ae436f8656d15fe78 +size 1840908288 diff --git a/Llama3.2-3B-ShiningValiant2.Q2_K.gguf b/Llama3.2-3B-ShiningValiant2.Q2_K.gguf new file mode 100644 index 0000000..cfaea37 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4288161e915e37762bcf95e736e9cacfbc4b43b8c715aa261ab1c2d48f80603 +size 1363937280 diff --git a/Llama3.2-3B-ShiningValiant2.Q3_K_L.gguf b/Llama3.2-3B-ShiningValiant2.Q3_K_L.gguf new file mode 100644 index 0000000..512b524 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8762842217d18de881efaa32822e35fe3e502a4dec4956e7914b837a9c39229 +size 1815349248 diff --git a/Llama3.2-3B-ShiningValiant2.Q3_K_M.gguf b/Llama3.2-3B-ShiningValiant2.Q3_K_M.gguf new file mode 100644 index 0000000..0810054 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a89b1824f282197a0548277bf0d2d4032034773e15cdfd6060dabd596059d1 +size 1687160832 diff --git a/Llama3.2-3B-ShiningValiant2.Q3_K_S.gguf b/Llama3.2-3B-ShiningValiant2.Q3_K_S.gguf new file mode 100644 index 0000000..dfb9961 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38e9b17fc184f69ee5805204c82231ed785be080cb146e2a972104a7373ad39 +size 1542850560 diff --git a/Llama3.2-3B-ShiningValiant2.Q4_0_4_4.gguf b/Llama3.2-3B-ShiningValiant2.Q4_0_4_4.gguf new file mode 100644 index 0000000..3391759 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3dc547681e70db19c599554c1df6074be0c7f7da4c4bc15c4fd602de352e6d +size 1917192192 diff --git a/Llama3.2-3B-ShiningValiant2.Q4_K_M.gguf b/Llama3.2-3B-ShiningValiant2.Q4_K_M.gguf new file mode 100644 index 0000000..8394566 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56a6563c464e2d3fab13e2a69244c8f393c22dbcdd28f8b74d89c5a4ac42468 +size 2019379200 diff --git a/Llama3.2-3B-ShiningValiant2.Q4_K_S.gguf b/Llama3.2-3B-ShiningValiant2.Q4_K_S.gguf new file mode 100644 index 0000000..1845738 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7fd019fb111d8cf303a74e4f0c7841bb65a5563acd5828f606cf664a4c8167 +size 1928202240 diff --git a/Llama3.2-3B-ShiningValiant2.Q5_K_M.gguf b/Llama3.2-3B-ShiningValiant2.Q5_K_M.gguf new file mode 100644 index 0000000..a66461b --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df84c7fb888602f7a4f1e8e392e53619d56585ffc360fd36e8cc799464bb8def +size 2322155520 diff --git a/Llama3.2-3B-ShiningValiant2.Q5_K_S.gguf b/Llama3.2-3B-ShiningValiant2.Q5_K_S.gguf new file mode 100644 index 0000000..31a1aca --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ae09cc7f1989567a6bf795d6819b156e3b779e9a869d98872ab3257b69c4e1 +size 2269513728 diff --git a/Llama3.2-3B-ShiningValiant2.Q6_K.gguf b/Llama3.2-3B-ShiningValiant2.Q6_K.gguf new file mode 100644 index 0000000..9144fb3 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb38a06cf83efbc77e1cb266725beaf25bfb0ec5ba4d3b8f31ded346eb35670 +size 2643855360 diff --git a/Llama3.2-3B-ShiningValiant2.Q8_0.gguf b/Llama3.2-3B-ShiningValiant2.Q8_0.gguf new file mode 100644 index 0000000..aef7ac7 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a725420efa6f44062d8811bc2b3ce0f9614f498be1a40daf7f0394ea1bf48390 +size 3421900800 diff --git a/Llama3.2-3B-ShiningValiant2.f16.gguf b/Llama3.2-3B-ShiningValiant2.f16.gguf new file mode 100644 index 0000000..0633278 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d6112d90e82d318797cd6df209d72f782b6ababfc83ab661e9eaf4841eae35 +size 6433689600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..396d783 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +base_model: ValiantLabs/Llama3.2-3B-ShiningValiant2 +datasets: +- sequelbox/Celestia +- sequelbox/Spurline +- sequelbox/Supernova +language: +- en +library_name: transformers +license: llama3.2 +model_type: llama +quantized_by: mradermacher +tags: +- shining-valiant +- shining-valiant-2 +- valiant +- valiant-labs +- llama +- llama-3.2 +- llama-3.2-instruct +- llama-3.2-instruct-3b +- llama-3 +- llama-3-instruct +- llama-3-instruct-3b +- 3b +- science +- physics +- biology +- chemistry +- compsci +- computer-science +- engineering +- technical +- conversational +- chat +- instruct +--- +## About + + + + + + +static quants of https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-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/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.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. + +