commit 8e21370aa5a2c4395de5a9e3ae9a4991bfd2fc22 Author: ModelHub XC Date: Fri Jun 12 23:56:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/blossom-v5-32b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..73f767f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +blossom-v5-32b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..99c3172 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Azure99/blossom-v5-32b +datasets: +- Azure99/blossom-chat-v3 +- Azure99/blossom-math-v4 +- Azure99/blossom-wizard-v3 +- Azure99/blossom-orca-v3 +language: +- zh +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Azure99/blossom-v5-32b + + +static quants are available at https://huggingface.co/mradermacher/blossom-v5-32b-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/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ1_S.gguf) | i1-IQ1_S | 7.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ2_S.gguf) | i1-IQ2_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q2_K.gguf) | i1-Q2_K | 12.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.7 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ3_S.gguf) | i1-IQ3_S | 14.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ3_M.gguf) | i1-IQ3_M | 14.8 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q4_0.gguf) | i1-Q4_0 | 18.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.6 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.2 | | +| [GGUF](https://huggingface.co/mradermacher/blossom-v5-32b-i1-GGUF/resolve/main/blossom-v5-32b.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/blossom-v5-32b.i1-IQ1_M.gguf b/blossom-v5-32b.i1-IQ1_M.gguf new file mode 100644 index 0000000..adb054f --- /dev/null +++ b/blossom-v5-32b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bceaf74ab6ce9cb5765bc8d73cff6e93d0fb3014da8631a4adbd28fcfbceb93 +size 7875961248 diff --git a/blossom-v5-32b.i1-IQ1_S.gguf b/blossom-v5-32b.i1-IQ1_S.gguf new file mode 100644 index 0000000..53b4498 --- /dev/null +++ b/blossom-v5-32b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a691d1fe40d60a5397ee0725c0138a55d8986f99e145fc75e8fad3fb7cf44cda +size 7223959968 diff --git a/blossom-v5-32b.i1-IQ2_M.gguf b/blossom-v5-32b.i1-IQ2_M.gguf new file mode 100644 index 0000000..5571973 --- /dev/null +++ b/blossom-v5-32b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b241f5450f76bae8791cf08d1ef9e9b2f7a6e85a7a47f8c7c682a84febbbda52 +size 11182682528 diff --git a/blossom-v5-32b.i1-IQ2_S.gguf b/blossom-v5-32b.i1-IQ2_S.gguf new file mode 100644 index 0000000..819479b --- /dev/null +++ b/blossom-v5-32b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a5615473a2390af0e6bb443225bf9d8826c0a6c821d2f5d993d28fed2b11264 +size 10313347488 diff --git a/blossom-v5-32b.i1-IQ2_XS.gguf b/blossom-v5-32b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..baa05b2 --- /dev/null +++ b/blossom-v5-32b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a409b95523790f4ff6c28524a12a91c28d37eca36d073cb952262b161010201 +size 9884393888 diff --git a/blossom-v5-32b.i1-IQ2_XXS.gguf b/blossom-v5-32b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..56c57d9 --- /dev/null +++ b/blossom-v5-32b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c6500fc279a8cb94a2e7bbd0e2e28e1f81486f4d88ebe1b6fba7c4a883be5e9 +size 8962630048 diff --git a/blossom-v5-32b.i1-IQ3_M.gguf b/blossom-v5-32b.i1-IQ3_M.gguf new file mode 100644 index 0000000..4f27911 --- /dev/null +++ b/blossom-v5-32b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df585a89a079e126a11f8d23187e2dd29c1425cdc9474b498131d40dabfc765 +size 14700593568 diff --git a/blossom-v5-32b.i1-IQ3_S.gguf b/blossom-v5-32b.i1-IQ3_S.gguf new file mode 100644 index 0000000..fe0407d --- /dev/null +++ b/blossom-v5-32b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64647d864b5c57f4a6143c20ea63553e0ce08719f9dfdef3b318cc210026b0fc +size 14328758688 diff --git a/blossom-v5-32b.i1-IQ3_XS.gguf b/blossom-v5-32b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..997b738 --- /dev/null +++ b/blossom-v5-32b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3c5a642cbadeb5516a150b5b64012a84daf1378d828cda304b4c6aafe72a0d +size 13603275168 diff --git a/blossom-v5-32b.i1-IQ3_XXS.gguf b/blossom-v5-32b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1e1a8b5 --- /dev/null +++ b/blossom-v5-32b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445851d93b4cb8407b01978c55fe6003ce6a03a27df60a772838ce34b7c693b6 +size 12742930848 diff --git a/blossom-v5-32b.i1-IQ4_XS.gguf b/blossom-v5-32b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8aa039e --- /dev/null +++ b/blossom-v5-32b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e0affeed13b098f751f6579f72bb326ae318a5d7116453d963d720bb2ff695e +size 17559458208 diff --git a/blossom-v5-32b.i1-Q2_K.gguf b/blossom-v5-32b.i1-Q2_K.gguf new file mode 100644 index 0000000..b190ea4 --- /dev/null +++ b/blossom-v5-32b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:013a089c236606aca018c43eb4778aed291a0b43c633712d531dbe7ab4000b59 +size 12222001568 diff --git a/blossom-v5-32b.i1-Q3_K_L.gguf b/blossom-v5-32b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..081ac32 --- /dev/null +++ b/blossom-v5-32b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc01a91d8ed3bd64a6630b5ec8d504cf0e1f30cb8f11790aec018f35f7310215 +size 17117315488 diff --git a/blossom-v5-32b.i1-Q3_K_M.gguf b/blossom-v5-32b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e898688 --- /dev/null +++ b/blossom-v5-32b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8353cfd8ceed9ca295eecaf4ab8f6dd109c2eadad0f2b0f3940f8a74de728e +size 15815115168 diff --git a/blossom-v5-32b.i1-Q3_K_S.gguf b/blossom-v5-32b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..db79f62 --- /dev/null +++ b/blossom-v5-32b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12879bda62fd28ba9cd9fc35f5c93d631ba1d7e3f7263f6639998ab2f2b611a8 +size 14284194208 diff --git a/blossom-v5-32b.i1-Q4_0.gguf b/blossom-v5-32b.i1-Q4_0.gguf new file mode 100644 index 0000000..62e86bb --- /dev/null +++ b/blossom-v5-32b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393df0f2567cce1399bfdc07f280e900f9d0bd5ab48c0972a745ed929880d06d +size 18568794528 diff --git a/blossom-v5-32b.i1-Q4_K_M.gguf b/blossom-v5-32b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..21d76d4 --- /dev/null +++ b/blossom-v5-32b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f40369eb08e85d0516a9aec1538e72a23244688595659b2c59ac64df5ff025b +size 19698962848 diff --git a/blossom-v5-32b.i1-Q4_K_S.gguf b/blossom-v5-32b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..86ed24e --- /dev/null +++ b/blossom-v5-32b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16c2f3179ee58b21596c28af3876928f25a2e1a10cccebb0541350018981b668 +size 18641539488 diff --git a/blossom-v5-32b.i1-Q5_K_M.gguf b/blossom-v5-32b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f608c55 --- /dev/null +++ b/blossom-v5-32b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06de94736c8d785977928f2af25ff64679623f853576c2166ba6177881050e6d +size 23083569568 diff --git a/blossom-v5-32b.i1-Q5_K_S.gguf b/blossom-v5-32b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..787a336 --- /dev/null +++ b/blossom-v5-32b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d043ea5c2aef33c0add913ea5bad95c621adad84829df735c201c824f63f359 +size 22465237408 diff --git a/blossom-v5-32b.i1-Q6_K.gguf b/blossom-v5-32b.i1-Q6_K.gguf new file mode 100644 index 0000000..d021338 --- /dev/null +++ b/blossom-v5-32b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd697007a4c8cd7aa948dedad0b16e193af5fb89cd4cfb9ef5518559267b3d6f +size 26679714208 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..04bc4e4 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3c9b4a1fc5df10bbe422ec5a1719bfb3b759cb79fc5b0b38888ff1a0e04fe2 +size 14891553