commit e4218e70cbfe314a5096823a0444f1c8aa6f6753 Author: ModelHub XC Date: Mon Jun 15 14:02:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d96e81a --- /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 +Qwen2.5-Ultra-1.5B-25.02-Exp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Ultra-1.5B-25.02-Exp.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.IQ4_XS.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.IQ4_XS.gguf new file mode 100644 index 0000000..940d38d --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6228312c5ad76d5a8d797b7d25ded1dcb0d9fb64bb4c23ff573925877e20b51d +size 902183968 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q2_K.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q2_K.gguf new file mode 100644 index 0000000..906e92f --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26af64f2cbba959218c612af27e7c839ae134600fe2f9a691f15c7d69d9ce1b6 +size 676305952 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_L.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_L.gguf new file mode 100644 index 0000000..bc53db7 --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ec08826509e1c4174ff7f72feea971afac36f82d774b1c2fc822fb33a781f9 +size 880163872 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_M.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_M.gguf new file mode 100644 index 0000000..06e7217 --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dee2bb26f526e6bb608ded88ad5c986d859f145162af0104bcd7b8250110a67 +size 824179744 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_S.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_S.gguf new file mode 100644 index 0000000..698b3ec --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50eb76b163fdb2e0f1c5008af0df989c79827d5210f160faee1f23f7b7434cbc +size 760945696 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_M.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_M.gguf new file mode 100644 index 0000000..428eeca --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb01647db931c4330636ba0553a4746a6177c78f5b379e77771c9ba61f3b3061 +size 986049568 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_S.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_S.gguf new file mode 100644 index 0000000..2c54d3f --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e2aa02e151794c839b9d1f36d16824c36c6551c6b4a73f87e677bddb2e25d1 +size 940313632 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_M.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_M.gguf new file mode 100644 index 0000000..42424cb --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015b9e3c687040aa707ee5484dead2d829aa13c074b8c7d49dc6c217ba804c5b +size 1125051424 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_S.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_S.gguf new file mode 100644 index 0000000..68edd5e --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed149f861413c9419039bcff6f6ee4da015fee424a994e603ef9adf9ae8740d3 +size 1098730528 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q6_K.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q6_K.gguf new file mode 100644 index 0000000..267036a --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68bcf3d54cc9f04daacad86738154c9b027c2271dfdec11c098e08bb947abc2a +size 1272740896 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.Q8_0.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q8_0.gguf new file mode 100644 index 0000000..3f93190 --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d6675b4bb7c3daec410ce3b7a26b76276184fab224bfaef5f5f7c404d742f40 +size 1646574112 diff --git a/Qwen2.5-Ultra-1.5B-25.02-Exp.f16.gguf b/Qwen2.5-Ultra-1.5B-25.02-Exp.f16.gguf new file mode 100644 index 0000000..d1cdd5d --- /dev/null +++ b/Qwen2.5-Ultra-1.5B-25.02-Exp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcb817c595015646f87bdc431c27ee29503b3465bab226adfc68829b6b91fa7 +size 3093670432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..02250c2 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp + + +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/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Ultra-1.5B-25.02-Exp-GGUF/resolve/main/Qwen2.5-Ultra-1.5B-25.02-Exp.f16.gguf) | f16 | 3.2 | 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. + +