commit 504579ee92e6e8879b19fa30d55176abe52c7874 Author: ModelHub XC Date: Wed Jul 15 19:52:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67568f9 --- /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 +Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-Math-7B-Max-v3-accuracy.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.IQ4_XS.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.IQ4_XS.gguf new file mode 100644 index 0000000..3343bf5 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da24a4389208c1cfc3b8003c2a9ebe1ae88c9e428878bbb7cca9a83a6e93e3ad +size 4250298880 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q2_K.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q2_K.gguf new file mode 100644 index 0000000..9f3ab40 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323ce6bcdcfacd5575de819cd195690c74dc26c051be148c61f3c8a81dc8ff3f +size 3015940608 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_L.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_L.gguf new file mode 100644 index 0000000..9c8d556 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b924324668b88c52e7af16ce9bc4b8694767ebf5980c62ce56ed38a36099dde +size 4088459776 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_M.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_M.gguf new file mode 100644 index 0000000..5a37e68 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05daa3dc3624082c84d876dc4efc7602e8824b90612883c8603d49f131efeefa +size 3808391680 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_S.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_S.gguf new file mode 100644 index 0000000..310ba65 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d65dabacf1f8c0535f2aa01d0599993a8335572644907308aa9a5637b99b6d +size 3492368896 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_M.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_M.gguf new file mode 100644 index 0000000..7273a6b --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0169627cadb9f316bec01dc894afe35d47b89454bd9330dac0b16e900c7adc03 +size 4683074048 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_S.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_S.gguf new file mode 100644 index 0000000..212e31f --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81ddafb618545b367618db91d8514261a8efe996858b46989eb71eb18de6705 +size 4457769472 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_M.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_M.gguf new file mode 100644 index 0000000..71b0525 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0c2a371a7ffeeac907a9ca60f4d036ecd6a8e060d6392625654d6155bd0eac +size 5444831744 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_S.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_S.gguf new file mode 100644 index 0000000..c549cda --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9ab4b4c2c80b5018f1b47459420747ec3e13f2e413d4155f1542cebcbe3245 +size 5315176960 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q6_K.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q6_K.gguf new file mode 100644 index 0000000..b55b23f --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc01c8fdb4c4cba3f982b6ad474f4c7fc04944f7e0d0fda06cbe0e951edbe1e +size 6254199296 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.Q8_0.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q8_0.gguf new file mode 100644 index 0000000..668f9ee --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4cb7903d55e29de65afbae4d566855b72da41dc77d927c47057b51b1e3ccab +size 8098525696 diff --git a/Qwen-2.5-Math-7B-Max-v3-accuracy.f16.gguf b/Qwen-2.5-Math-7B-Max-v3-accuracy.f16.gguf new file mode 100644 index 0000000..8f4b824 --- /dev/null +++ b/Qwen-2.5-Math-7B-Max-v3-accuracy.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7b88f8653e5d6ad02d70bed5b23e8c895ff740879927cf16bf96ff92d69735 +size 15237853696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b13ff3 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: cg666/Qwen-2.5-Math-7B-Max-v3-accuracy +datasets: DigitalLearningGmbH/MATH-lighteval +language: +- en +library_name: transformers +model_name: Qwen-2.5-Math-7B-Max-v3-accuracy +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/cg666/Qwen-2.5-Math-7B-Max-v3-accuracy + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF).*** + +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/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-Math-7B-Max-v3-accuracy-GGUF/resolve/main/Qwen-2.5-Math-7B-Max-v3-accuracy.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. + +