commit 7629dc090b4dd5e3fd01e5e74ff045eeeaab709a Author: ModelHub XC Date: Mon Jun 1 09:22:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChineseErrorCorrector4-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..235a50d --- /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 +ChineseErrorCorrector4-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChineseErrorCorrector4-4B.IQ4_XS.gguf b/ChineseErrorCorrector4-4B.IQ4_XS.gguf new file mode 100644 index 0000000..8f3ee2f --- /dev/null +++ b/ChineseErrorCorrector4-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7bf5fda148bf0a93453b028766ca6524088b5664aa1c89976ae309c18531a4 +size 2286315616 diff --git a/ChineseErrorCorrector4-4B.Q2_K.gguf b/ChineseErrorCorrector4-4B.Q2_K.gguf new file mode 100644 index 0000000..753dbe8 --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6ed59a2f368c78ee95be0eaf9197281d307c5d31558088cab0783ce6ccfc71 +size 1669498976 diff --git a/ChineseErrorCorrector4-4B.Q3_K_L.gguf b/ChineseErrorCorrector4-4B.Q3_K_L.gguf new file mode 100644 index 0000000..41ac7a2 --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b1ef145f8b3f04e082e508960320f8bc0a76932ab7f1f30a3502ab45d6b451 +size 2239785056 diff --git a/ChineseErrorCorrector4-4B.Q3_K_M.gguf b/ChineseErrorCorrector4-4B.Q3_K_M.gguf new file mode 100644 index 0000000..93317f1 --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11fd055257edc7c19b042943b75fb284d2997ee50c9c2878d2f8f385ec9839a +size 2075617376 diff --git a/ChineseErrorCorrector4-4B.Q3_K_S.gguf b/ChineseErrorCorrector4-4B.Q3_K_S.gguf new file mode 100644 index 0000000..a50c134 --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8733fda7d66c657a715de8c9c397e78c4a8028711c6828083365efc99410bc05 +size 1886996576 diff --git a/ChineseErrorCorrector4-4B.Q4_K_M.gguf b/ChineseErrorCorrector4-4B.Q4_K_M.gguf new file mode 100644 index 0000000..cffbd8c --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b86247b60c844140944610cec31806f3c21150c9d53ca91d914dbc23a5c188db +size 2497280096 diff --git a/ChineseErrorCorrector4-4B.Q4_K_S.gguf b/ChineseErrorCorrector4-4B.Q4_K_S.gguf new file mode 100644 index 0000000..3d4d09f --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03be8e71517a80c30b4304e8042bc6d3868fc2fe4f9406baea09332d36755c07 +size 2383308896 diff --git a/ChineseErrorCorrector4-4B.Q5_K_M.gguf b/ChineseErrorCorrector4-4B.Q5_K_M.gguf new file mode 100644 index 0000000..a3b0f1a --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec07994fba355a6657b516a458745e5343284f3f91d113d1a57d771571bd515 +size 2889513056 diff --git a/ChineseErrorCorrector4-4B.Q5_K_S.gguf b/ChineseErrorCorrector4-4B.Q5_K_S.gguf new file mode 100644 index 0000000..1e3aa37 --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ae5db0169b5dff71aed0509e9c1f1eaf872426e004f0cc8ea3df0894bed14a +size 2823710816 diff --git a/ChineseErrorCorrector4-4B.Q6_K.gguf b/ChineseErrorCorrector4-4B.Q6_K.gguf new file mode 100644 index 0000000..486269d --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba49b65581a321c7afd1d313c2ba134e6eaad727b452d93aafb6b68859da6a10 +size 3306260576 diff --git a/ChineseErrorCorrector4-4B.Q8_0.gguf b/ChineseErrorCorrector4-4B.Q8_0.gguf new file mode 100644 index 0000000..05b1a1a --- /dev/null +++ b/ChineseErrorCorrector4-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d22475b344aeb327edccb38c546eac4f7914c2af1b79b96086193c9dda9a4c9 +size 4280404576 diff --git a/ChineseErrorCorrector4-4B.f16.gguf b/ChineseErrorCorrector4-4B.f16.gguf new file mode 100644 index 0000000..bdc561b --- /dev/null +++ b/ChineseErrorCorrector4-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40161ca5c6812bd35a9ee9d2e03166ae3cc7e20525131585a121f54c0701bfbb +size 8051284576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ba2d48 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: twnlp/ChineseErrorCorrector4-4B +datasets: +- twnlp/ChineseErrorCorrector +language: +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chinese +- text-correction +- grammatical-error-correction +- spelling-check +- qwen3 +- chain-of-thought +- reinforcement-learning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/twnlp/ChineseErrorCorrector4-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ChineseErrorCorrector4-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-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/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-GGUF/resolve/main/ChineseErrorCorrector4-4B.f16.gguf) | f16 | 8.2 | 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. + +