commit 6f1bc79ead1ae3a17f6c8ed13a6ebd472474ac56 Author: ModelHub XC Date: Sat Apr 11 00:01:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..678a54b --- /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 +Upcycled-Qwen1.5-MoE2.7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Upcycled-Qwen1.5-MoE2.7B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..56252db --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-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/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q2_K.gguf) | Q2_K | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q3_K_S.gguf) | Q3_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q3_K_L.gguf) | Q3_K_L | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.IQ4_XS.gguf) | IQ4_XS | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 8.1 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q4_K_M.gguf) | Q4_K_M | 9.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q5_K_S.gguf) | Q5_K_S | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q5_K_M.gguf) | Q5_K_M | 10.7 | | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q6_K.gguf) | Q6_K | 12.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q8_0.gguf) | Q8_0 | 15.0 | fast, best quality | + +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/Upcycled-Qwen1.5-MoE2.7B.IQ4_XS.gguf b/Upcycled-Qwen1.5-MoE2.7B.IQ4_XS.gguf new file mode 100644 index 0000000..e521498 --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46a5ec7dd93e04527c54f6883ae3291c29530e2c28648613f6b05a9179cce23 +size 7788705088 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q2_K.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q2_K.gguf new file mode 100644 index 0000000..e6a60ca --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce5677f8e2e0ec3eed5bfb038a5c3d4be20bdafeb54f8856d0f80758cbc9a79f +size 5804246336 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q3_K_L.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q3_K_L.gguf new file mode 100644 index 0000000..c9927cd --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54de52a55bcf6a5aa6b14e57b261462c6bff1869b116f1227f0cfd116f6a1745 +size 7599029568 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q3_K_M.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q3_K_M.gguf new file mode 100644 index 0000000..333ac59 --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f26f8b40003f5847605fe5fe4e4650c68d29517b2d944e51256ce229b6aba4 +size 7315651904 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q3_K_S.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q3_K_S.gguf new file mode 100644 index 0000000..4f497de --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ed37f3c32935b7de2e126913d9bf8f5c76e7b00edc8820c4707af0e5f2b138 +size 6735527232 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q4_0_4_4.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q4_0_4_4.gguf new file mode 100644 index 0000000..9cb6bba --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2541fa90042858399e68b6bad6d905ba43d5dd67bef0a67ab10c2b8f41ed13c6 +size 7980094784 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q4_K_M.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q4_K_M.gguf new file mode 100644 index 0000000..580c2de --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2abb518a5fb5740c9d0b898add22440aecd23753d72f8771a8f597950a0c8e6d +size 9345733952 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q4_K_S.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q4_K_S.gguf new file mode 100644 index 0000000..af6e209 --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465a2bb2044c424b9277bae66b585f7868c9cd61a96dbbed6c911b27632dc213 +size 8557073728 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q5_K_M.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q5_K_M.gguf new file mode 100644 index 0000000..aa54bcd --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e41416c93585d6c713e74f0fd932758703f0d9f96d5160539adb160db16e03 +size 10646066496 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q5_K_S.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q5_K_S.gguf new file mode 100644 index 0000000..9118d3b --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0362ffc2b5969b6ced22d524c7c6d35f00981638edaa192d05928ffcb0cf4313 +size 9963050304 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q6_K.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q6_K.gguf new file mode 100644 index 0000000..cb1685f --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a3528a4e8ed68832d487ee99e1c3cf1751f1e476a72128f63e8ee41849c259 +size 12560280896 diff --git a/Upcycled-Qwen1.5-MoE2.7B.Q8_0.gguf b/Upcycled-Qwen1.5-MoE2.7B.Q8_0.gguf new file mode 100644 index 0000000..9eae79f --- /dev/null +++ b/Upcycled-Qwen1.5-MoE2.7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f16a249f8d6d9336214ec4ecccbb87ff0d4cbee234271896607c050f4fb790 +size 14905146688