commit 50da2ddd658b4c767bb1219fad3df617ab2eeaaa Author: ModelHub XC Date: Sat Jun 13 21:34:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dolphin3-Llama3.2-Smart-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..22c4dd7 --- /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 +Dolphin3-Llama3.2-Smart.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3-Llama3.2-Smart.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dolphin3-Llama3.2-Smart.IQ4_XS.gguf b/Dolphin3-Llama3.2-Smart.IQ4_XS.gguf new file mode 100644 index 0000000..6055d10 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699415bf0da7ba036ac1fc1fa5b29bb36c1cab5ed4518267c602320e1cd643fa +size 1840908992 diff --git a/Dolphin3-Llama3.2-Smart.Q2_K.gguf b/Dolphin3-Llama3.2-Smart.Q2_K.gguf new file mode 100644 index 0000000..ff33c38 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a14a9317b509b36631c9c0b6f127d234448ec97bf3179759d4d445c93a8f1c1 +size 1363937984 diff --git a/Dolphin3-Llama3.2-Smart.Q3_K_L.gguf b/Dolphin3-Llama3.2-Smart.Q3_K_L.gguf new file mode 100644 index 0000000..ad965e4 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e5ac2f7e257e5b514835862eff3743db8fbf4081798840f0461d3f0d8dfbb5 +size 1815349952 diff --git a/Dolphin3-Llama3.2-Smart.Q3_K_M.gguf b/Dolphin3-Llama3.2-Smart.Q3_K_M.gguf new file mode 100644 index 0000000..8f1b3f5 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a8d2d3fe2cf52b5bd9bdbd7222343fe7bcd9df0eecaef766c9f215fff1775e +size 1687161536 diff --git a/Dolphin3-Llama3.2-Smart.Q3_K_S.gguf b/Dolphin3-Llama3.2-Smart.Q3_K_S.gguf new file mode 100644 index 0000000..5cd0510 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02c7433b4210ead0a1f139d7e3d21c9d690eca26aa759f208a2fc7b55ccfe3a +size 1542851264 diff --git a/Dolphin3-Llama3.2-Smart.Q4_K_M.gguf b/Dolphin3-Llama3.2-Smart.Q4_K_M.gguf new file mode 100644 index 0000000..4cb1aa7 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d7ba47862fbcdbdeaacb87f0af7c306527c7338bb056e34367649307b384df +size 2019379904 diff --git a/Dolphin3-Llama3.2-Smart.Q4_K_S.gguf b/Dolphin3-Llama3.2-Smart.Q4_K_S.gguf new file mode 100644 index 0000000..9b806fc --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c881e5ec07920e7862167b836c7cb962d8c2c1f7a6e9d75d7ab8668800976b71 +size 1928202944 diff --git a/Dolphin3-Llama3.2-Smart.Q5_K_M.gguf b/Dolphin3-Llama3.2-Smart.Q5_K_M.gguf new file mode 100644 index 0000000..aacea8b --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f9a06e5aa244dc1a0c5ec9b155f50ce85865696ea4ff70f0e1511a6b7bc86d +size 2322156224 diff --git a/Dolphin3-Llama3.2-Smart.Q5_K_S.gguf b/Dolphin3-Llama3.2-Smart.Q5_K_S.gguf new file mode 100644 index 0000000..986f4d7 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5643e2cf303a0db7f723dac3da3752ce4c1f8a49aeae3362b3d6319847f01c +size 2269514432 diff --git a/Dolphin3-Llama3.2-Smart.Q6_K.gguf b/Dolphin3-Llama3.2-Smart.Q6_K.gguf new file mode 100644 index 0000000..ebeaec7 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9b9ee3cfc63181d946acfcbc4ecdeabe6db5eed0d635891fe4a74dac55177f +size 2643856064 diff --git a/Dolphin3-Llama3.2-Smart.Q8_0.gguf b/Dolphin3-Llama3.2-Smart.Q8_0.gguf new file mode 100644 index 0000000..8249f84 --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398ab0f4d52da0eebffd248ac5ab781797bfed116a5085f8dc50ea4e34a15603 +size 3421902976 diff --git a/Dolphin3-Llama3.2-Smart.f16.gguf b/Dolphin3-Llama3.2-Smart.f16.gguf new file mode 100644 index 0000000..53eb05a --- /dev/null +++ b/Dolphin3-Llama3.2-Smart.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f5fffa4de959af5b1eec4c5f085a9f2b1fb850b7adbd157e2c2fd234b0b4366 +size 6433697536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d638096 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Triangle104/Dolphin3-Llama3.2-Smart +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Triangle104/Dolphin3-Llama3.2-Smart + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-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/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3-Llama3.2-Smart-GGUF/resolve/main/Dolphin3-Llama3.2-Smart.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. + +