commit d6fff5877be01103df6fd87476bcd3adc58a9e09 Author: ModelHub XC Date: Wed Apr 22 13:03:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Korean-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..50d939f --- /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 +Qwen2.5-3B-Korean.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Korean.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Korean.IQ4_XS.gguf b/Qwen2.5-3B-Korean.IQ4_XS.gguf new file mode 100644 index 0000000..8f63823 --- /dev/null +++ b/Qwen2.5-3B-Korean.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8fd153485b1bf3f317dc7b5a069286d6f0c7d5944167b354bbaab884c5842e +size 1753185824 diff --git a/Qwen2.5-3B-Korean.Q2_K.gguf b/Qwen2.5-3B-Korean.Q2_K.gguf new file mode 100644 index 0000000..65dede2 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95d8faedc21c8d7f16f5f30d181eef18e37fb90872b172669b2ff0506043b9b +size 1274756640 diff --git a/Qwen2.5-3B-Korean.Q3_K_L.gguf b/Qwen2.5-3B-Korean.Q3_K_L.gguf new file mode 100644 index 0000000..528bb0c --- /dev/null +++ b/Qwen2.5-3B-Korean.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b617e3e824cdf20453e5a4b3fcd3410587790476a1d837633ca41b0e3f6f6147 +size 1707392544 diff --git a/Qwen2.5-3B-Korean.Q3_K_M.gguf b/Qwen2.5-3B-Korean.Q3_K_M.gguf new file mode 100644 index 0000000..5c837c9 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e70964fece9cbf2a8cbb81e345d88d633dfc3befeec5efc807b1ef41a8fc32 +size 1590476320 diff --git a/Qwen2.5-3B-Korean.Q3_K_S.gguf b/Qwen2.5-3B-Korean.Q3_K_S.gguf new file mode 100644 index 0000000..63a78d1 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be01ba3d1050c022bd25f5eaeb5d08b194b20ebf04841144110963404b99a6b +size 1454358048 diff --git a/Qwen2.5-3B-Korean.Q4_K_M.gguf b/Qwen2.5-3B-Korean.Q4_K_M.gguf new file mode 100644 index 0000000..c9a7d58 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96a4b8b468fe0030cd09aa72cced74b74312929477d8904e3db1a791a4e6adc +size 1929903648 diff --git a/Qwen2.5-3B-Korean.Q4_K_S.gguf b/Qwen2.5-3B-Korean.Q4_K_S.gguf new file mode 100644 index 0000000..22272cb --- /dev/null +++ b/Qwen2.5-3B-Korean.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94f38418f62ba386fb641a9cbd644a217ca8c77a59f43adff9465238e46fedb +size 1834384928 diff --git a/Qwen2.5-3B-Korean.Q5_K_M.gguf b/Qwen2.5-3B-Korean.Q5_K_M.gguf new file mode 100644 index 0000000..bd6227f --- /dev/null +++ b/Qwen2.5-3B-Korean.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812509c907be8357ac570a8ce31472d526d76c1adecb22246d59ade1793ac727 +size 2224815648 diff --git a/Qwen2.5-3B-Korean.Q5_K_S.gguf b/Qwen2.5-3B-Korean.Q5_K_S.gguf new file mode 100644 index 0000000..dda9c49 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8bc916bff77129473f21a8d5048e34e15d6ecd613d212670626da2e9273ac7 +size 2169667104 diff --git a/Qwen2.5-3B-Korean.Q6_K.gguf b/Qwen2.5-3B-Korean.Q6_K.gguf new file mode 100644 index 0000000..3ea96d0 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd94d480602bd226013d78292175268e722cf9b35522bc146ff628c4170c5d0c +size 2538159648 diff --git a/Qwen2.5-3B-Korean.Q8_0.gguf b/Qwen2.5-3B-Korean.Q8_0.gguf new file mode 100644 index 0000000..f7d70f5 --- /dev/null +++ b/Qwen2.5-3B-Korean.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f99ff171926cf94b96ba48707ff1344a8746a8a79f86922d06add50f9c8fda70 +size 3285476896 diff --git a/Qwen2.5-3B-Korean.f16.gguf b/Qwen2.5-3B-Korean.f16.gguf new file mode 100644 index 0000000..33d6da0 --- /dev/null +++ b/Qwen2.5-3B-Korean.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f588e25e68d94374c2441564bbdfe0545e7a8aff85001f12c9cd7e70ea946e0b +size 6178317856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..faeed26 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: MyeongHo0621/Qwen2.5-3B-Korean +datasets: +- MyeongHo0621/smol-koreantalk +language: +- ko +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen +- qwen2.5 +- korean +- merged +- gguf +- conversational +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MyeongHo0621/Qwen2.5-3B-Korean + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-3B-Korean-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/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Korean-GGUF/resolve/main/Qwen2.5-3B-Korean.f16.gguf) | f16 | 6.3 | 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. + +