commit c87afd5d971cb67f2efd5664cc21f9cebcf979a1 Author: ModelHub XC Date: Thu Jun 18 14:50:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..55058ac --- /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 +FuseChat-Llama-3.2-3B-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseChat-Llama-3.2-3B-SFT.IQ4_XS.gguf b/FuseChat-Llama-3.2-3B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..e5846a1 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d919d0abfaa5ebcbb5921126a8ab7856dd07207901723e883444c45a3275dec +size 1840903520 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q2_K.gguf b/FuseChat-Llama-3.2-3B-SFT.Q2_K.gguf new file mode 100644 index 0000000..e917acb --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8b277ff1ac9b569390cb6c122285ba0331a7b0a6183dfe2d778ce0ddc023c2 +size 1363932512 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q3_K_L.gguf b/FuseChat-Llama-3.2-3B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..16b2d9f --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c4912ed5cc13f5f58e9b0e7201a6d1249ed4f7b58d99eaebad9eb1bf74fa48 +size 1815344480 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q3_K_M.gguf b/FuseChat-Llama-3.2-3B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..e47cf87 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3a020ee0cd5cfd578a92a6f797ee77971b864f7cad55e7e680b8c137fd6ef5 +size 1687156064 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q3_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..25e911f --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5eb071a4440524ae3dee153583d82e2172e56577638656055c3f8e8e4a2c90d +size 1542845792 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q4_K_M.gguf b/FuseChat-Llama-3.2-3B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..9463fd9 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb2aed9267209e01d8c47ca295ae138b7e2b0d6ed630b2320c231465d0c0bd5 +size 2019374432 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q4_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..a6ebc11 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f168d2857fb09d111e91ef23259cc656ab04fc4a1cde1d6e0befbce3a26ecbd5 +size 1928197472 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q5_K_M.gguf b/FuseChat-Llama-3.2-3B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..92e64d8 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:204d025b65e234fd23833ae91f6a02595428b02fdbdb5da77077a203771985ac +size 2322150752 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q5_K_S.gguf b/FuseChat-Llama-3.2-3B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..223baf5 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610b2aba1e2b74f05e3153fb4f14e037287e6f10ab0c578251c50940a3502784 +size 2269508960 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q6_K.gguf b/FuseChat-Llama-3.2-3B-SFT.Q6_K.gguf new file mode 100644 index 0000000..df9765c --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d1b33056552c7cbf560070ea990690995e98c9250797195995bf6c039a81f1 +size 2643850592 diff --git a/FuseChat-Llama-3.2-3B-SFT.Q8_0.gguf b/FuseChat-Llama-3.2-3B-SFT.Q8_0.gguf new file mode 100644 index 0000000..6ec81a9 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e68220e0f1ece5088a704d9d7ac4f2510d6a2a67e2758e3062a71d5971a4065 +size 3421896032 diff --git a/FuseChat-Llama-3.2-3B-SFT.f16.gguf b/FuseChat-Llama-3.2-3B-SFT.f16.gguf new file mode 100644 index 0000000..a8518e9 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e0f836709b95ba785f29cf8ec5cb9471625d9b0a4fadeb3d6548f6fb71df64 +size 6433684832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00b9871 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: FuseAI/FuseChat-Llama-3.2-3B-SFT +datasets: +- FuseAI/FuseChat-3.0-SFT-Data +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/FuseAI/FuseChat-Llama-3.2-3B-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-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/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-3B-SFT.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. + +