commit 995f2385638d16b358e05fea8ba0ca8f519f6d3b Author: ModelHub XC Date: Tue Jul 21 00:48:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Mini-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c2a5ad7 --- /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 +Qwen2.5-7B-Mini.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Mini.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Mini.IQ4_XS.gguf b/Qwen2.5-7B-Mini.IQ4_XS.gguf new file mode 100644 index 0000000..9f5e9ac --- /dev/null +++ b/Qwen2.5-7B-Mini.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6384fbe129029356b9c785819542603da752ed6407ab13ed3a2fc167f0bc131 +size 1611528832 diff --git a/Qwen2.5-7B-Mini.Q2_K.gguf b/Qwen2.5-7B-Mini.Q2_K.gguf new file mode 100644 index 0000000..cdb7ab2 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ecb6d81219b65a589fdb0a487cef1365b34721c0722d008bcd78e986542c9e +size 1227868800 diff --git a/Qwen2.5-7B-Mini.Q3_K_L.gguf b/Qwen2.5-7B-Mini.Q3_K_L.gguf new file mode 100644 index 0000000..0296065 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e820e813d7688d141273dc2ff943a61ba895696d2539bb899017c3a1dbdc4f50 +size 1537512064 diff --git a/Qwen2.5-7B-Mini.Q3_K_M.gguf b/Qwen2.5-7B-Mini.Q3_K_M.gguf new file mode 100644 index 0000000..d2de375 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dcdf4667813853135c597c15696f754bdbc17cb4eb31ecf8baf7a692c057a1d +size 1465717376 diff --git a/Qwen2.5-7B-Mini.Q3_K_S.gguf b/Qwen2.5-7B-Mini.Q3_K_S.gguf new file mode 100644 index 0000000..d3fbdc1 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79edf37936bd4a0a6d3a28b183ea4dc70261dfce13550ac42571221624d5d86 +size 1388489344 diff --git a/Qwen2.5-7B-Mini.Q4_K_M.gguf b/Qwen2.5-7B-Mini.Q4_K_M.gguf new file mode 100644 index 0000000..899cc77 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718fbb8b2329a6a204496f7518fcea8cd9fbb2498ba0a5b85d338b0452d84811 +size 1731463808 diff --git a/Qwen2.5-7B-Mini.Q4_K_S.gguf b/Qwen2.5-7B-Mini.Q4_K_S.gguf new file mode 100644 index 0000000..22f6b11 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80fbdff4b402168cf9f0b39f42e12f01a14df22d12cbc205b71ac5d90298ec13 +size 1678449280 diff --git a/Qwen2.5-7B-Mini.Q5_K_M.gguf b/Qwen2.5-7B-Mini.Q5_K_M.gguf new file mode 100644 index 0000000..0c86fcd --- /dev/null +++ b/Qwen2.5-7B-Mini.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d7426397d3fb3acea1852c25ed4750adc6b6dda988373fbf1b0e2e8cd50744 +size 1977354880 diff --git a/Qwen2.5-7B-Mini.Q5_K_S.gguf b/Qwen2.5-7B-Mini.Q5_K_S.gguf new file mode 100644 index 0000000..b96648c --- /dev/null +++ b/Qwen2.5-7B-Mini.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a31a1befd4700e10b4de5996762a959dc936859a54685b552171d501bdc2a5 +size 1949571712 diff --git a/Qwen2.5-7B-Mini.Q6_K.gguf b/Qwen2.5-7B-Mini.Q6_K.gguf new file mode 100644 index 0000000..88be066 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e686d2f55dd04be86658f5ab57a9c273e550ca2316670c34aded165152642e4a +size 2238614144 diff --git a/Qwen2.5-7B-Mini.Q8_0.gguf b/Qwen2.5-7B-Mini.Q8_0.gguf new file mode 100644 index 0000000..c1cefc6 --- /dev/null +++ b/Qwen2.5-7B-Mini.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6d5746e31bdfd55ab872ab155ff24f127bdb2b2a2e893c686f996536f37127 +size 2897683072 diff --git a/Qwen2.5-7B-Mini.f16.gguf b/Qwen2.5-7B-Mini.f16.gguf new file mode 100644 index 0000000..d5b3907 --- /dev/null +++ b/Qwen2.5-7B-Mini.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b618f1809998687eac051e5b16e30c539421012fecc01ddf98fe5896a4f6f66c +size 5448917632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1b166c8 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Sakalti/Qwen2.5-7B-Mini +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Sakalti/Qwen2.5-7B-Mini + + +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/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q4_K_S.gguf) | Q4_K_S | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.Q8_0.gguf) | Q8_0 | 3.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Mini-GGUF/resolve/main/Qwen2.5-7B-Mini.f16.gguf) | f16 | 5.5 | 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. + +