From e3765186893e5d4507181188f234e6f470ad2cc5 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 23 May 2026 22:54:21 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++ Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q4_K_S.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf | 3 ++ Qwen2.5-Math-7B-Instruct-32k.f16.gguf | 3 ++ README.md | 64 ++++++++++++++++++++++++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q4_K_S.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf create mode 100644 Qwen2.5-Math-7B-Instruct-32k.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2b10f0b --- /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-Math-7B-Instruct-32k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf b/Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf new file mode 100644 index 0000000..032d2fd --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6255459068b21d7928d16d68455d68d89678be3bc338c86d67586e02829e9ba0 +size 4250298816 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf new file mode 100644 index 0000000..b062ed6 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358aec53ece10a71857b08fd1ce45b21b1eebd50ae9d428684b08bbc3f8c8201 +size 3015940544 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf new file mode 100644 index 0000000..c904beb --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f00e93d4eac44f6a0ca7a5631c580717a30332b80bae0025b0ff27c1cf9c0ac +size 4088459712 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf new file mode 100644 index 0000000..0356475 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f8289aee34ba597cdb2539c818dc3597baf1bfd65cce58f648b840d477086f +size 3808391616 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf new file mode 100644 index 0000000..2bef9d7 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e227ea42eefb6a64e4632a365c33902d4f6a686726d1cdd8963182a1c5d4b2 +size 3492368832 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf new file mode 100644 index 0000000..a748801 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50fc07cc0603fc247560e7be926fd6575a9d202820f521a89d94dcd98757ded +size 4683073984 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q4_K_S.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q4_K_S.gguf new file mode 100644 index 0000000..9319031 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e3f901ac1466485629a2115ecdc59258a811e35b2163c42da98d62d69585dc +size 4457769408 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf new file mode 100644 index 0000000..8e46782 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d14c6f4bd962a1e6601c201f80e1454e4a6fb93d553a1c41e3ba789ee156f5f +size 5444831680 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf new file mode 100644 index 0000000..0c90c81 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41ff0c6dc32732302988feb8580435442cca76e05761bf9a479cadbc5bef64c +size 5315176896 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf new file mode 100644 index 0000000..d01138e --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e5af2abf5775c08147b17f14a3d1c02369f3e030862ee932288ba3e8821719 +size 6254199232 diff --git a/Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf b/Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf new file mode 100644 index 0000000..8ad7120 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f89b3fd53f3563ecf689a5916ec9982adb841a1077ef103fc482beb2ddd1ccbe +size 8098525632 diff --git a/Qwen2.5-Math-7B-Instruct-32k.f16.gguf b/Qwen2.5-Math-7B-Instruct-32k.f16.gguf new file mode 100644 index 0000000..8e6d953 --- /dev/null +++ b/Qwen2.5-Math-7B-Instruct-32k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b11d26b4ba9ef8b721d1cc96469e2d7169d331c1c886915141e23029389d601 +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..67df7bd --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: InfiniAILab/Qwen2.5-Math-7B-Instruct-32k +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/InfiniAILab/Qwen2.5-Math-7B-Instruct-32k + + +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-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-Instruct-32k-GGUF/resolve/main/Qwen2.5-Math-7B-Instruct-32k.f16.gguf) | f16 | 15.3 | 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. + +