commit 9d5640171c0d3d8f09e2ac955ae9c1f973313439 Author: ModelHub XC Date: Sun Apr 12 22:58:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-1.5Moe-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..51adfbd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Qwen2-1.5Moe.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5Moe.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-1.5Moe.IQ3_M.gguf b/Qwen2-1.5Moe.IQ3_M.gguf new file mode 100644 index 0000000..a89e8c7 --- /dev/null +++ b/Qwen2-1.5Moe.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c014a3c64a3716d86d24b9d5f4510c0e34d9768be086750a5f0e2d796570544 +size 1881917824 diff --git a/Qwen2-1.5Moe.IQ3_S.gguf b/Qwen2-1.5Moe.IQ3_S.gguf new file mode 100644 index 0000000..97226a6 --- /dev/null +++ b/Qwen2-1.5Moe.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7494fef582e2c8de8de4a69cf27922ab2ec40cb439fc6b404d77294b8f552ff +size 1856693632 diff --git a/Qwen2-1.5Moe.IQ3_XS.gguf b/Qwen2-1.5Moe.IQ3_XS.gguf new file mode 100644 index 0000000..82b1484 --- /dev/null +++ b/Qwen2-1.5Moe.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4936a2537cb77c298a3521c4d27bd2a1a1fe1f7565aec72d28facab46b9ca3e1 +size 1771795840 diff --git a/Qwen2-1.5Moe.IQ4_XS.gguf b/Qwen2-1.5Moe.IQ4_XS.gguf new file mode 100644 index 0000000..4889092 --- /dev/null +++ b/Qwen2-1.5Moe.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2756ac9ff2ce65442d52830303628ac3dc4db49f0213abcf8338901f839303 +size 2267897728 diff --git a/Qwen2-1.5Moe.Q2_K.gguf b/Qwen2-1.5Moe.Q2_K.gguf new file mode 100644 index 0000000..f09457b --- /dev/null +++ b/Qwen2-1.5Moe.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714669c4e7a2e4e6a3e95d757feac659196d3b40f293d23d961fb6a13263e3b6 +size 1590340480 diff --git a/Qwen2-1.5Moe.Q3_K_L.gguf b/Qwen2-1.5Moe.Q3_K_L.gguf new file mode 100644 index 0000000..166dc31 --- /dev/null +++ b/Qwen2-1.5Moe.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d71c889d0df5fe6c331dad4c847a62270ab653c940482446bc3349d8963e669 +size 2173146496 diff --git a/Qwen2-1.5Moe.Q3_K_M.gguf b/Qwen2-1.5Moe.Q3_K_M.gguf new file mode 100644 index 0000000..671b182 --- /dev/null +++ b/Qwen2-1.5Moe.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0ff6085efeb36f1c3709b575c3c9cfad137e6e6ad837d9972ab2c74c9c8a0b +size 2024265088 diff --git a/Qwen2-1.5Moe.Q3_K_S.gguf b/Qwen2-1.5Moe.Q3_K_S.gguf new file mode 100644 index 0000000..ad90765 --- /dev/null +++ b/Qwen2-1.5Moe.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c212f475209a8a1e470f4b7bae706f7d28f51a75a068e0929e4a95d8dcf187 +size 1855231360 diff --git a/Qwen2-1.5Moe.Q4_K_M.gguf b/Qwen2-1.5Moe.Q4_K_M.gguf new file mode 100644 index 0000000..b5362f8 --- /dev/null +++ b/Qwen2-1.5Moe.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e8928749772771f01b48e1ccd8146f200df3b781089e7cbb679c618a4ab0a9 +size 2517755776 diff --git a/Qwen2-1.5Moe.Q4_K_S.gguf b/Qwen2-1.5Moe.Q4_K_S.gguf new file mode 100644 index 0000000..4449978 --- /dev/null +++ b/Qwen2-1.5Moe.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d6f7ce0886d83021957eec11a7bd4b2280c6ce74714e6f75c4274e5b905be8 +size 2382993280 diff --git a/Qwen2-1.5Moe.Q5_K_M.gguf b/Qwen2-1.5Moe.Q5_K_M.gguf new file mode 100644 index 0000000..2451e10 --- /dev/null +++ b/Qwen2-1.5Moe.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8473a326c41d90ffb1436b4316aab2a3619afc7b662a0c8ae09486385014d36 +size 2926774144 diff --git a/Qwen2-1.5Moe.Q5_K_S.gguf b/Qwen2-1.5Moe.Q5_K_S.gguf new file mode 100644 index 0000000..fa194bb --- /dev/null +++ b/Qwen2-1.5Moe.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288a5dd7487924e189a168facc5d72ee02c95296378ee03f6038008dad67a097 +size 2849273728 diff --git a/Qwen2-1.5Moe.Q6_K.gguf b/Qwen2-1.5Moe.Q6_K.gguf new file mode 100644 index 0000000..2a63ce4 --- /dev/null +++ b/Qwen2-1.5Moe.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac9c52ec616a43204c26589b46b4c62b54d7c2d2066c64182cfa9a93a0800e6 +size 3361356160 diff --git a/Qwen2-1.5Moe.Q8_0.gguf b/Qwen2-1.5Moe.Q8_0.gguf new file mode 100644 index 0000000..9f5d722 --- /dev/null +++ b/Qwen2-1.5Moe.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef68ac293bc5511220293a5c191fa514b7f1533fb7864c96f704f621be5f296 +size 4351673728 diff --git a/Qwen2-1.5Moe.f16.gguf b/Qwen2-1.5Moe.f16.gguf new file mode 100644 index 0000000..7fae081 --- /dev/null +++ b/Qwen2-1.5Moe.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337c3d798b9b6002cd59707de44d46e8247a960f003c40e682897c32aacff917 +size 8185161088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0babfea --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: femiari/Qwen2-1.5Moe +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- moe +- frankenmoe +- merge +- mergekit +- lazymergekit +- Qwen/Qwen2-1.5B +- Replete-AI/Replete-Coder-Qwen2-1.5b +--- +## About + + + + + + +static quants of https://huggingface.co/femiari/Qwen2-1.5Moe + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.IQ3_XS.gguf) | IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.IQ3_S.gguf) | IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.IQ3_M.gguf) | IQ3_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q6_K.gguf) | Q6_K | 3.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.Q8_0.gguf) | Q8_0 | 4.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5Moe-GGUF/resolve/main/Qwen2-1.5Moe.f16.gguf) | f16 | 8.3 | 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. + +