commit 3621c4c49c3807fffcd9ab5274b62f8c757022d8 Author: ModelHub XC Date: Sat Jun 13 02:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KRX-Qwen2.5-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2beb232 --- /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 +KRX-Qwen2.5-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KRX-Qwen2.5-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KRX-Qwen2.5-7B.IQ4_XS.gguf b/KRX-Qwen2.5-7B.IQ4_XS.gguf new file mode 100644 index 0000000..8f7defb --- /dev/null +++ b/KRX-Qwen2.5-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987938d720701a6efcedd87d90c7b148822b9d99abe0789e9b831ed358f485ab +size 4248361728 diff --git a/KRX-Qwen2.5-7B.Q2_K.gguf b/KRX-Qwen2.5-7B.Q2_K.gguf new file mode 100644 index 0000000..07a1422 --- /dev/null +++ b/KRX-Qwen2.5-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74b8312e8166d7210fcd856b0e0e208fda921f5302916a69d9df69bc174d043 +size 3014293216 diff --git a/KRX-Qwen2.5-7B.Q3_K_L.gguf b/KRX-Qwen2.5-7B.Q3_K_L.gguf new file mode 100644 index 0000000..3fbaa3f --- /dev/null +++ b/KRX-Qwen2.5-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac057b07dcdadb039dbb756232f50246fc7ed03e7a48599d272472f5ab1ec6a8 +size 4086667520 diff --git a/KRX-Qwen2.5-7B.Q3_K_M.gguf b/KRX-Qwen2.5-7B.Q3_K_M.gguf new file mode 100644 index 0000000..564c769 --- /dev/null +++ b/KRX-Qwen2.5-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c547a933826189b383d6219fb0aac7e327e265a573be4ec77e6a5e689ed98dd2 +size 3806599424 diff --git a/KRX-Qwen2.5-7B.Q3_K_S.gguf b/KRX-Qwen2.5-7B.Q3_K_S.gguf new file mode 100644 index 0000000..6ee282b --- /dev/null +++ b/KRX-Qwen2.5-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae807d20ae94f0355a7b855ea183055c8544be466d09ad0e65fb3c31a2e91aa +size 3490576640 diff --git a/KRX-Qwen2.5-7B.Q4_K_M.gguf b/KRX-Qwen2.5-7B.Q4_K_M.gguf new file mode 100644 index 0000000..d337ebd --- /dev/null +++ b/KRX-Qwen2.5-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf528832bf5e400aeede2b45fcd8447712355af1c31585b003836ca1b723ca6 +size 4681092320 diff --git a/KRX-Qwen2.5-7B.Q4_K_S.gguf b/KRX-Qwen2.5-7B.Q4_K_S.gguf new file mode 100644 index 0000000..8cea7dc --- /dev/null +++ b/KRX-Qwen2.5-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cc095171ef02869e5ea9ff5cc5328d5f61ca49173edc4a76836195262f7e15 +size 4455787744 diff --git a/KRX-Qwen2.5-7B.Q5_K_M.gguf b/KRX-Qwen2.5-7B.Q5_K_M.gguf new file mode 100644 index 0000000..a865910 --- /dev/null +++ b/KRX-Qwen2.5-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f6fe01d0985b3e9073a2c596e3a4f973bffaa203661a3352ec0e309a50c3f5 +size 5442671712 diff --git a/KRX-Qwen2.5-7B.Q5_K_S.gguf b/KRX-Qwen2.5-7B.Q5_K_S.gguf new file mode 100644 index 0000000..b0c2a36 --- /dev/null +++ b/KRX-Qwen2.5-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428b12eb4bbb058afa76427e7e05b22965b59d326a8fcea14d747bd3e9ca4c93 +size 5313016928 diff --git a/KRX-Qwen2.5-7B.Q6_K.gguf b/KRX-Qwen2.5-7B.Q6_K.gguf new file mode 100644 index 0000000..150f9be --- /dev/null +++ b/KRX-Qwen2.5-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0feff9bca979345d9b5ef2ac82047e75c30daf549a589d814e7c138211ffce52 +size 6251849824 diff --git a/KRX-Qwen2.5-7B.Q8_0.gguf b/KRX-Qwen2.5-7B.Q8_0.gguf new file mode 100644 index 0000000..0e1b34b --- /dev/null +++ b/KRX-Qwen2.5-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f288583bb95133ea0cb4b8b2d8859a5b10ca60ffa36f594da929778c0c386ff4 +size 8095485280 diff --git a/KRX-Qwen2.5-7B.f16.gguf b/KRX-Qwen2.5-7B.f16.gguf new file mode 100644 index 0000000..e16a1da --- /dev/null +++ b/KRX-Qwen2.5-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f30771cc5d0e689c75a9f4db0f128da246052660b0ba0bbd7a18bc3c5cfadf0 +size 15232138720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6511509 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: SeoSaMo/KRX-Qwen2.5-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SeoSaMo/KRX-Qwen2.5-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KRX-Qwen2.5-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-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/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KRX-Qwen2.5-7B-GGUF/resolve/main/KRX-Qwen2.5-7B.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. + +