commit f9a1b654ee9e6dee00e2eb461be1dad24f68e89c Author: ModelHub XC Date: Wed May 6 00:40:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..55c4db6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-14B-Instruct-Preview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct-Preview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Math-14B-Instruct-Preview.IQ4_XS.gguf b/Qwen2.5-Math-14B-Instruct-Preview.IQ4_XS.gguf new file mode 100644 index 0000000..af912db --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56576a93fd8678a18ed556890c2617ec8caf6eaf76c5032b758a27a199bfb1c8 +size 8186196352 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q2_K.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q2_K.gguf new file mode 100644 index 0000000..29cc376 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5072620784a26283cd85f9d3b0de7cd8ac842676218514300f6b9361270e49 +size 5770498432 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_L.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_L.gguf new file mode 100644 index 0000000..a8298db --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc3e6633138cb99d5c182f8b7ca44f478fc90afd564fb9315a07c29de74f4c1 +size 7924769152 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_M.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_M.gguf new file mode 100644 index 0000000..8a091d9 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e889d3bed00859b4c7689d7c2f382b2286af6cef1d35ca176f7c80383ee4622 +size 7339204992 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_S.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_S.gguf new file mode 100644 index 0000000..f814c9c --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b94b1b4de3461af49a3a4363842b91ed50508045cf286e754994ea5f01f43cd +size 6659596672 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_M.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_M.gguf new file mode 100644 index 0000000..924acfd --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b388ac70664c93548311bb8f09699ae264cd3159b77abb7f333d63bbf494906 +size 8988111232 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_S.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_S.gguf new file mode 100644 index 0000000..5057266 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2e653236d0bbdc4e01180094f8c7d497992616f0308931dc91079a5376bbe7d +size 8573432192 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_M.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_M.gguf new file mode 100644 index 0000000..91fd348 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90b68cf43742aca9c42277ed5f872d32b92641373865da341fe29cc80cc15db +size 10508874112 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_S.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_S.gguf new file mode 100644 index 0000000..8f7653b --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d178dd1f49c38096bbf37a0f813d135deb3305d19247d546c9b74eeeff500a85 +size 10266554752 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q6_K.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q6_K.gguf new file mode 100644 index 0000000..e14f63f --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466a545a52a370af74392dd9e61077c0a9bf35287eaa7e065a66e6780d63df19 +size 12124684672 diff --git a/Qwen2.5-Math-14B-Instruct-Preview.Q8_0.gguf b/Qwen2.5-Math-14B-Instruct-Preview.Q8_0.gguf new file mode 100644 index 0000000..86ba6eb --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct-Preview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad41699e9057fe6b092d4e73a62b04c7fe3978fd2799da3613bc3c60993cd913 +size 15701598592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b9fbae5 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: qingy2024/Qwen2.5-Math-14B-Instruct-Preview +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/qingy2024/Qwen2.5-Math-14B-Instruct-Preview + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-i1-GGUF +## 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-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q2_K.gguf) | Q2_K | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_S.gguf) | Q3_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q3_K_L.gguf) | Q3_K_L | 8.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.IQ4_XS.gguf) | IQ4_XS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_S.gguf) | Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q5_K_M.gguf) | Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q6_K.gguf) | Q6_K | 12.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-Preview-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct-Preview.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality | + +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. + +