commit 7cb83ec51780ec797251bb11b2e8a87093658959 Author: ModelHub XC Date: Thu May 7 02:19:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-UFO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f088445 --- /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 +Qwen2.5-3B-UFO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-UFO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-UFO.IQ4_XS.gguf b/Qwen2.5-3B-UFO.IQ4_XS.gguf new file mode 100644 index 0000000..9ec3f65 --- /dev/null +++ b/Qwen2.5-3B-UFO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222f22fc2d02bb673785bff5ee344f553fc121e5d083791f7ee2939c9e3efc59 +size 1753185504 diff --git a/Qwen2.5-3B-UFO.Q2_K.gguf b/Qwen2.5-3B-UFO.Q2_K.gguf new file mode 100644 index 0000000..30ed252 --- /dev/null +++ b/Qwen2.5-3B-UFO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e011ccb900b9de12af6a1e1cca0e8068a28c2eed89d472e51cc84b6102aa9e +size 1274756320 diff --git a/Qwen2.5-3B-UFO.Q3_K_L.gguf b/Qwen2.5-3B-UFO.Q3_K_L.gguf new file mode 100644 index 0000000..d29988f --- /dev/null +++ b/Qwen2.5-3B-UFO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e6feb0fd7174266db03bca0ba20323868ee247d2f8a6117079adf958c1b9a55 +size 1707392224 diff --git a/Qwen2.5-3B-UFO.Q3_K_M.gguf b/Qwen2.5-3B-UFO.Q3_K_M.gguf new file mode 100644 index 0000000..329d2bf --- /dev/null +++ b/Qwen2.5-3B-UFO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513b34da4bb39b41677590dd4cdb21db87199f8c175907bb3a3611f5eeb48ab6 +size 1590476000 diff --git a/Qwen2.5-3B-UFO.Q3_K_S.gguf b/Qwen2.5-3B-UFO.Q3_K_S.gguf new file mode 100644 index 0000000..0856d06 --- /dev/null +++ b/Qwen2.5-3B-UFO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05adef5811364add909c8faebcede47e6ebf0d5e6936695cc866949abfa988b +size 1454357728 diff --git a/Qwen2.5-3B-UFO.Q4_K_M.gguf b/Qwen2.5-3B-UFO.Q4_K_M.gguf new file mode 100644 index 0000000..16be959 --- /dev/null +++ b/Qwen2.5-3B-UFO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d515b5fce2a071d8c771adab6920f09e0b741f4638b6c14917e6ee47578db9 +size 1929903328 diff --git a/Qwen2.5-3B-UFO.Q4_K_S.gguf b/Qwen2.5-3B-UFO.Q4_K_S.gguf new file mode 100644 index 0000000..18ca97d --- /dev/null +++ b/Qwen2.5-3B-UFO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd711eba7d82aa4f9bd4ba949b215f26d79accfcc94bc00a0fd76f219c98d9c2 +size 1834384608 diff --git a/Qwen2.5-3B-UFO.Q5_K_M.gguf b/Qwen2.5-3B-UFO.Q5_K_M.gguf new file mode 100644 index 0000000..40bb1c4 --- /dev/null +++ b/Qwen2.5-3B-UFO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7b431895ef3a593c1ca22aabbf7e1345344992dedc2c043e70cfe128e34ea5 +size 2224815328 diff --git a/Qwen2.5-3B-UFO.Q5_K_S.gguf b/Qwen2.5-3B-UFO.Q5_K_S.gguf new file mode 100644 index 0000000..d63ae31 --- /dev/null +++ b/Qwen2.5-3B-UFO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:979cb4023655e17e368f1c23c80968e41cc5326b977cf501c51d243f59f661a6 +size 2169666784 diff --git a/Qwen2.5-3B-UFO.Q6_K.gguf b/Qwen2.5-3B-UFO.Q6_K.gguf new file mode 100644 index 0000000..ed91c38 --- /dev/null +++ b/Qwen2.5-3B-UFO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d331825eb1e2b1f3f2dc7b1a977d465aad269d7bab563fd1dadb812cdb50a44 +size 2538159328 diff --git a/Qwen2.5-3B-UFO.Q8_0.gguf b/Qwen2.5-3B-UFO.Q8_0.gguf new file mode 100644 index 0000000..32a9cdf --- /dev/null +++ b/Qwen2.5-3B-UFO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:855dfddc1adec25e395e18eddca0ffd4f1d62137c4ec4a41654fe3458f796df9 +size 3285476576 diff --git a/Qwen2.5-3B-UFO.f16.gguf b/Qwen2.5-3B-UFO.f16.gguf new file mode 100644 index 0000000..4774cba --- /dev/null +++ b/Qwen2.5-3B-UFO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e292bcfa7e06a574043d74fe70db2989a74770c4950169464f751c7d200b75 +size 6178317536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a00a1ef --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: LichengLiu03/Qwen2.5-3B-UFO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- qwen2.5 +- ppo +- rlhf +- metamath +- math +- reasoning +- verl +--- +## About + + + + + + +static quants of https://huggingface.co/LichengLiu03/Qwen2.5-3B-UFO + + +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/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-UFO-GGUF/resolve/main/Qwen2.5-3B-UFO.f16.gguf) | f16 | 6.3 | 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. + +