commit 5c14981faee1eca015d01d9dd7162824f1db0e50 Author: ModelHub XC Date: Tue Sep 29 10:43:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/multillama-3.2-merge-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..356aed1 --- /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 +multillama-3.2-merge.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +multillama-3.2-merge.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b80b4a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: SFBAI/multillama-3.2-merge +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/SFBAI/multillama-3.2-merge + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/multillama-3.2-merge-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/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/multillama-3.2-merge-GGUF/resolve/main/multillama-3.2-merge.f16.gguf) | f16 | 7.3 | 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. + + diff --git a/multillama-3.2-merge.IQ4_XS.gguf b/multillama-3.2-merge.IQ4_XS.gguf new file mode 100644 index 0000000..6f8b894 --- /dev/null +++ b/multillama-3.2-merge.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc327d1d3f4c6fc3ca378628b06b6e8bfff59a95cf0127c6fd6cfb3302fb6d2 +size 2050222624 diff --git a/multillama-3.2-merge.Q2_K.gguf b/multillama-3.2-merge.Q2_K.gguf new file mode 100644 index 0000000..9898927 --- /dev/null +++ b/multillama-3.2-merge.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e33958be95c97be46f5d34ec925a59d1286646296729ffa13e2971ebafc801 +size 1493219872 diff --git a/multillama-3.2-merge.Q3_K_L.gguf b/multillama-3.2-merge.Q3_K_L.gguf new file mode 100644 index 0000000..2949279 --- /dev/null +++ b/multillama-3.2-merge.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97e5bec35a0cc14952769f0f525843b80e9f2ed77acfe894aa08074c2844c5b +size 1984647712 diff --git a/multillama-3.2-merge.Q3_K_M.gguf b/multillama-3.2-merge.Q3_K_M.gguf new file mode 100644 index 0000000..78e903a --- /dev/null +++ b/multillama-3.2-merge.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf31316bca14841db09f6b2cdbbf1ab12a6da726b772173b34151b13e7171e3f +size 1856459296 diff --git a/multillama-3.2-merge.Q3_K_S.gguf b/multillama-3.2-merge.Q3_K_S.gguf new file mode 100644 index 0000000..fd92d90 --- /dev/null +++ b/multillama-3.2-merge.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9803d38276282be26eaa19be434f501a86010e0cadd14bca0dc79bcc0186d484 +size 1712149024 diff --git a/multillama-3.2-merge.Q4_K_M.gguf b/multillama-3.2-merge.Q4_K_M.gguf new file mode 100644 index 0000000..cd4c2c0 --- /dev/null +++ b/multillama-3.2-merge.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd683258f909d3f27c1ca0fa227bba9f62cb8fcdc7654612827f4a08d9e2460a +size 2241006112 diff --git a/multillama-3.2-merge.Q4_K_S.gguf b/multillama-3.2-merge.Q4_K_S.gguf new file mode 100644 index 0000000..08640bd --- /dev/null +++ b/multillama-3.2-merge.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2318e90792f2f189c20148c1c3ee025e388c0f9ccd5f0ae08049f9bd649a8f +size 2149829152 diff --git a/multillama-3.2-merge.Q5_K_M.gguf b/multillama-3.2-merge.Q5_K_M.gguf new file mode 100644 index 0000000..c8fb358 --- /dev/null +++ b/multillama-3.2-merge.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a2cecf1e992d1b266cfd0f195a16feacfda4e8cc0ac7dd22e5a0b465f148a5 +size 2593032736 diff --git a/multillama-3.2-merge.Q5_K_S.gguf b/multillama-3.2-merge.Q5_K_S.gguf new file mode 100644 index 0000000..b1c5129 --- /dev/null +++ b/multillama-3.2-merge.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5c9d55ddf5cb6f3d689980e4b6a201a701df7aa08e7bf738d585eca1ab23cc +size 2540390944 diff --git a/multillama-3.2-merge.Q6_K.gguf b/multillama-3.2-merge.Q6_K.gguf new file mode 100644 index 0000000..840e9e4 --- /dev/null +++ b/multillama-3.2-merge.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c8f65b755feccb2993286219f16ccd346223c2cd61566f1f827d54268fb49e +size 2967061024 diff --git a/multillama-3.2-merge.Q8_0.gguf b/multillama-3.2-merge.Q8_0.gguf new file mode 100644 index 0000000..17d47e4 --- /dev/null +++ b/multillama-3.2-merge.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d20aa066b3ced240ae0eef9f54fa8aa64fbce774ceba0516f0d10863a3fff51 +size 3840528928 diff --git a/multillama-3.2-merge.f16.gguf b/multillama-3.2-merge.f16.gguf new file mode 100644 index 0000000..064a2b4 --- /dev/null +++ b/multillama-3.2-merge.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914255dacfd110861708114c2932c83edafc5389d6ad99e070edb280f9e39bf7 +size 7221695008