commit 7782d630b3127330b01b185118d475897a6224e7 Author: ModelHub XC Date: Sat Sep 26 03:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Breeze-7B-32k-Base-v1_0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..463b59e --- /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 +Breeze-7B-32k-Base-v1_0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.f16.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Breeze-7B-32k-Base-v1_0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Breeze-7B-32k-Base-v1_0.IQ4_XS.gguf b/Breeze-7B-32k-Base-v1_0.IQ4_XS.gguf new file mode 100644 index 0000000..470344d --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220781f6e45b53a3b222bbdc2f48917fc2fd7bfc30ce85a607b6eb1c41c8f698 +size 4113680000 diff --git a/Breeze-7B-32k-Base-v1_0.Q2_K.gguf b/Breeze-7B-32k-Base-v1_0.Q2_K.gguf new file mode 100644 index 0000000..94cf865 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3736397201528dd8659fb49f74ec8d6fd0ef1703bd3c8382846b4fe4b1ec2c03 +size 2863187584 diff --git a/Breeze-7B-32k-Base-v1_0.Q3_K_L.gguf b/Breeze-7B-32k-Base-v1_0.Q3_K_L.gguf new file mode 100644 index 0000000..aedc022 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19dbeb9be821dfe704c3903a94624af815a7af396711500e06d0658a9e82925 +size 3978643072 diff --git a/Breeze-7B-32k-Base-v1_0.Q3_K_M.gguf b/Breeze-7B-32k-Base-v1_0.Q3_K_M.gguf new file mode 100644 index 0000000..bf6bc66 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4818810596110e4b36d64c965571252aa56f0e27919370ffab320262e665e039 +size 3675604608 diff --git a/Breeze-7B-32k-Base-v1_0.Q3_K_S.gguf b/Breeze-7B-32k-Base-v1_0.Q3_K_S.gguf new file mode 100644 index 0000000..b5067c5 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee79b31651da8b0c7ad66d916cc7ccc53d8761bc5152563e8ae728580080493 +size 3321185920 diff --git a/Breeze-7B-32k-Base-v1_0.Q4_K_M.gguf b/Breeze-7B-32k-Base-v1_0.Q4_K_M.gguf new file mode 100644 index 0000000..ca7bc37 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbac41ff46fd5d698ffcdfeb2c77dbf964f60ec43d6508cf7aa385b48df5e83 +size 4541630080 diff --git a/Breeze-7B-32k-Base-v1_0.Q4_K_S.gguf b/Breeze-7B-32k-Base-v1_0.Q4_K_S.gguf new file mode 100644 index 0000000..9b78139 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841d7da695e27b53767bae162737d01a376494af25cedf2d7146c2ae0c54678b +size 4313564800 diff --git a/Breeze-7B-32k-Base-v1_0.Q5_K_M.gguf b/Breeze-7B-32k-Base-v1_0.Q5_K_M.gguf new file mode 100644 index 0000000..d6e282f --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cb333bf1caa77e90d3fe2ed9b2f3657776322c1d0e28e5747519f859817902 +size 5320197760 diff --git a/Breeze-7B-32k-Base-v1_0.Q5_K_S.gguf b/Breeze-7B-32k-Base-v1_0.Q5_K_S.gguf new file mode 100644 index 0000000..24f0f0f --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72b96c4930c3a2d441a774a793b68de6507706bd25dc4ac98272e7811136f57 +size 5186504320 diff --git a/Breeze-7B-32k-Base-v1_0.Q6_K.gguf b/Breeze-7B-32k-Base-v1_0.Q6_K.gguf new file mode 100644 index 0000000..7c2c508 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038369dde6828ce412860f8e62d2d45767453c10f5d105fb0c29c1ac108c2c03 +size 6147425920 diff --git a/Breeze-7B-32k-Base-v1_0.Q8_0.gguf b/Breeze-7B-32k-Base-v1_0.Q8_0.gguf new file mode 100644 index 0000000..2199c73 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc51501e4086a1d3790c766fb537532c4c4df1fbdcbf87ecd34488084f0bfee +size 7961659008 diff --git a/Breeze-7B-32k-Base-v1_0.f16.gguf b/Breeze-7B-32k-Base-v1_0.f16.gguf new file mode 100644 index 0000000..6e1fbc9 --- /dev/null +++ b/Breeze-7B-32k-Base-v1_0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029b2fe537ae296cda838b2acc3c89ae0822744addc1d9bcc005fc8282f5d5d8 +size 14984496768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb5881e --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: MediaTek-Research/Breeze-7B-32k-Base-v1_0 +language: +- zh +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/MediaTek-Research/Breeze-7B-32k-Base-v1_0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-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/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.IQ4_XS.gguf) | IQ4_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q5_K_S.gguf) | Q5_K_S | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q5_K_M.gguf) | Q5_K_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q6_K.gguf) | Q6_K | 6.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Breeze-7B-32k-Base-v1_0-GGUF/resolve/main/Breeze-7B-32k-Base-v1_0.f16.gguf) | f16 | 15.1 | 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. 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. + +