commit a56596847dc1cc48a4489b6e25c8c3422ed7a233 Author: ModelHub XC Date: Fri Aug 21 21:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-mini-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f14738 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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-mini-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-mini-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-mini-Instruct.IQ4_XS.gguf b/Qwen2.5-mini-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..66b1778 --- /dev/null +++ b/Qwen2.5-mini-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68349cf91b4aa713b1b1b16b929df2e2aa3a507773fa483426d62569f36927ae +size 3494849472 diff --git a/Qwen2.5-mini-Instruct.Q2_K.gguf b/Qwen2.5-mini-Instruct.Q2_K.gguf new file mode 100644 index 0000000..23cbd37 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0282d1c989f155c9b59d7b5c9cb4cdb30e73ad5ee9716ce74bca3438336a4c +size 2505063360 diff --git a/Qwen2.5-mini-Instruct.Q3_K_L.gguf b/Qwen2.5-mini-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..4a7cf66 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb8bb66111d63c6a9742ff26a0dee6ebe3fada674280645c24cd1774480fdfab +size 3359617984 diff --git a/Qwen2.5-mini-Instruct.Q3_K_M.gguf b/Qwen2.5-mini-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..79aedef --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bc921158f8d555119e825d673bd3a40bfc73398a6b8b8b9417efc1fb3c31c7 +size 3141481408 diff --git a/Qwen2.5-mini-Instruct.Q3_K_S.gguf b/Qwen2.5-mini-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..2dbccd9 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6d7101c9040c9f5adbe85b0b33ea8d974ac29dc9f8c8c485da600d8ae9aaaa +size 2891260864 diff --git a/Qwen2.5-mini-Instruct.Q4_K_M.gguf b/Qwen2.5-mini-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..cd6b96b --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a513106bcfea148b047be99b4fbbefeb2067d54f450426b75872dec98dc691 +size 3824348096 diff --git a/Qwen2.5-mini-Instruct.Q4_K_S.gguf b/Qwen2.5-mini-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..6116cb7 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e7f4092cbc64bb1689964891d74a5056be1565e62559ef65b83c522c8a5560 +size 3662465984 diff --git a/Qwen2.5-mini-Instruct.Q5_K_M.gguf b/Qwen2.5-mini-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..6cc3471 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d8cd3071de084a3fd268a5e7365d34cf79d696ca389f9d3ba2e6b1b3d24496 +size 4446186432 diff --git a/Qwen2.5-mini-Instruct.Q5_K_S.gguf b/Qwen2.5-mini-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..4ff7b0f --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4dcd26ed6ddc311c3989efe510c25f7e01e185017ecddc3fe03fa5c9fc5875 +size 4353575872 diff --git a/Qwen2.5-mini-Instruct.Q6_K.gguf b/Qwen2.5-mini-Instruct.Q6_K.gguf new file mode 100644 index 0000000..ecbc096 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26006a78760a2dbf0e0c943789ed6bf0d8b9ebd46e3db182d6e65cdf43a3eeda +size 5106889664 diff --git a/Qwen2.5-mini-Instruct.Q8_0.gguf b/Qwen2.5-mini-Instruct.Q8_0.gguf new file mode 100644 index 0000000..6e8eaa9 --- /dev/null +++ b/Qwen2.5-mini-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363bf5fbdeade502f4f9f47a71e7427245992528dffaaa794069b73e20f61a46 +size 6612571072 diff --git a/Qwen2.5-mini-Instruct.f16.gguf b/Qwen2.5-mini-Instruct.f16.gguf new file mode 100644 index 0000000..0e04748 --- /dev/null +++ b/Qwen2.5-mini-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2431a6b6ea4a558302d962788e87b65388255383e81ed7f0311d40334adef2a5 +size 12441015232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..96ad5f1 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: win10/Qwen2.5-mini-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Qwen/Qwen2.5-7B-Instruct +--- +## About + + + + + + +static quants of https://huggingface.co/win10/Qwen2.5-mini-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-mini-Instruct-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/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q4_K_M.gguf) | Q4_K_M | 3.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q5_K_M.gguf) | Q5_K_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q6_K.gguf) | Q6_K | 5.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.Q8_0.gguf) | Q8_0 | 6.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-mini-Instruct-GGUF/resolve/main/Qwen2.5-mini-Instruct.f16.gguf) | f16 | 12.5 | 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. + +