commit 3d7ed8e5038bdb3d0bcaa7e57865af3d280340ed Author: ModelHub XC Date: Sat May 30 12:43:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChineseErrorCorrector4-4B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7565ef --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChineseErrorCorrector4-4B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChineseErrorCorrector4-4B.i1-IQ1_M.gguf b/ChineseErrorCorrector4-4B.i1-IQ1_M.gguf new file mode 100644 index 0000000..80687b4 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f8888fd1aa1b083ad82f1159fb8d80a00a962c40165b52cd839e612ad5a291 +size 1127017312 diff --git a/ChineseErrorCorrector4-4B.i1-IQ1_S.gguf b/ChineseErrorCorrector4-4B.i1-IQ1_S.gguf new file mode 100644 index 0000000..b91fa16 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45aafa12fb4634e616261e33fab4207341711d030e18aca58092028c3f7d5c01 +size 1055255392 diff --git a/ChineseErrorCorrector4-4B.i1-IQ2_M.gguf b/ChineseErrorCorrector4-4B.i1-IQ2_M.gguf new file mode 100644 index 0000000..d6ad1b5 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6f4c840356c50958549722d8237b29ba1ca98021223bb060d1b127a41f0694 +size 1512983392 diff --git a/ChineseErrorCorrector4-4B.i1-IQ2_S.gguf b/ChineseErrorCorrector4-4B.i1-IQ2_S.gguf new file mode 100644 index 0000000..652c809 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f66c751a71ac4336ab5630093815f2c9b93ed85542515b5124822d3e2667de +size 1417300832 diff --git a/ChineseErrorCorrector4-4B.i1-IQ2_XS.gguf b/ChineseErrorCorrector4-4B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e753869 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74e252de074e386e7e147fba67b98142e45178cacce1f1b5894d09b87fbae08 +size 1354099552 diff --git a/ChineseErrorCorrector4-4B.i1-IQ2_XXS.gguf b/ChineseErrorCorrector4-4B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c3c4e2d --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccce1d3152dfcf3362285ceac19b823ca9e696c4b4f270dd4f0b9e6cee29cf2 +size 1246620512 diff --git a/ChineseErrorCorrector4-4B.i1-IQ3_M.gguf b/ChineseErrorCorrector4-4B.i1-IQ3_M.gguf new file mode 100644 index 0000000..d72fdad --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9edb2772b002a3f0b003ef5241ac5dc405bfd2553dc4daea90b8a4631c5f364 +size 1962895712 diff --git a/ChineseErrorCorrector4-4B.i1-IQ3_S.gguf b/ChineseErrorCorrector4-4B.i1-IQ3_S.gguf new file mode 100644 index 0000000..5567bfa --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0146ffbd5e4c0d38ff88163721fea6bb39c04f28879dd84895a0ab9056ed7779 +size 1899530592 diff --git a/ChineseErrorCorrector4-4B.i1-IQ3_XS.gguf b/ChineseErrorCorrector4-4B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..af06bc7 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0151f44ba3aa2e2f0817d5e1f9fbf87e88b0e1e107deb4736237dcc831766796 +size 1814374752 diff --git a/ChineseErrorCorrector4-4B.i1-IQ3_XXS.gguf b/ChineseErrorCorrector4-4B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..371f02f --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac48f6b9475e7d4221ea4ad74d9fb962089dc9cd48d8921b645f1a6f606edcf +size 1670187872 diff --git a/ChineseErrorCorrector4-4B.i1-IQ4_NL.gguf b/ChineseErrorCorrector4-4B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..9fd38d1 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc96ac491f5381f18c759eb1af29b92253ea1c162dd7cf60df78e41f9c7dbf8 +size 2381343072 diff --git a/ChineseErrorCorrector4-4B.i1-IQ4_XS.gguf b/ChineseErrorCorrector4-4B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5403fe6 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2afc614c0f9f7869d6a60c2c7b4a96e561c7d6d1aa7153080d3d76bc2b18343e +size 2270751072 diff --git a/ChineseErrorCorrector4-4B.i1-Q2_K.gguf b/ChineseErrorCorrector4-4B.i1-Q2_K.gguf new file mode 100644 index 0000000..3e230e1 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee2942a5a0f7ed6a34783529ecc0120c5be6c51a5fd77fa03e88b1fbe8d0a51 +size 1669499232 diff --git a/ChineseErrorCorrector4-4B.i1-Q2_K_S.gguf b/ChineseErrorCorrector4-4B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9b1b2fd --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5631659277a33a27a14b42b7b257b5936e2e5a31d51dbfa8a725f61ce0db731 +size 1563453792 diff --git a/ChineseErrorCorrector4-4B.i1-Q3_K_L.gguf b/ChineseErrorCorrector4-4B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..490814e --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5b42d80c76b87ee79f745c772d264d111c9835798960bf2788fccf6d5c367d +size 2239785312 diff --git a/ChineseErrorCorrector4-4B.i1-Q3_K_M.gguf b/ChineseErrorCorrector4-4B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..43bb6e3 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9f1754ea96f2ca7ec75a2d6782e80dd0251df66c949c7aefeeec3364540f3e +size 2075617632 diff --git a/ChineseErrorCorrector4-4B.i1-Q3_K_S.gguf b/ChineseErrorCorrector4-4B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7b43277 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f2dd7eedac414b0c8604a3f0dea728e506fc83852c89eaddf4b5b1e493cbaf +size 1886996832 diff --git a/ChineseErrorCorrector4-4B.i1-Q4_0.gguf b/ChineseErrorCorrector4-4B.i1-Q4_0.gguf new file mode 100644 index 0000000..9b9efa9 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0005e76ebc22fcf049a6d84f71da90e4bda5de94eed984ac0cb068860cdcac6 +size 2375772512 diff --git a/ChineseErrorCorrector4-4B.i1-Q4_1.gguf b/ChineseErrorCorrector4-4B.i1-Q4_1.gguf new file mode 100644 index 0000000..6e39026 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c31ed27004193efd2486f6b478cf85a9b40f66bf0b32d153a978460aff6e5a +size 2596628832 diff --git a/ChineseErrorCorrector4-4B.i1-Q4_K_M.gguf b/ChineseErrorCorrector4-4B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ea23f83 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183b67976a7ba4bc1a455fa39ba83724292f236585f49fd4c7d77624d60fb9e6 +size 2497280352 diff --git a/ChineseErrorCorrector4-4B.i1-Q4_K_S.gguf b/ChineseErrorCorrector4-4B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..157fc75 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d1677f2295da949aabb42d745a5cec847411936ccbeb04240220bcd3355494 +size 2383309152 diff --git a/ChineseErrorCorrector4-4B.i1-Q5_K_M.gguf b/ChineseErrorCorrector4-4B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7d54e4f --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0fa27fbdaa02ecddd7a5772fd528d99e6d96957f9f50dbe7cac492d8c9be21 +size 2889513312 diff --git a/ChineseErrorCorrector4-4B.i1-Q5_K_S.gguf b/ChineseErrorCorrector4-4B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..05a9fbd --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b593a2235ef0ccb59225a8e397acfac077e54698391dcbc2fbab8fde40066e2 +size 2823711072 diff --git a/ChineseErrorCorrector4-4B.i1-Q6_K.gguf b/ChineseErrorCorrector4-4B.i1-Q6_K.gguf new file mode 100644 index 0000000..d0e9b32 --- /dev/null +++ b/ChineseErrorCorrector4-4B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c11f864bc22c5f9cf88c7cc5d7b548d7c0b3e8b14888a226c02b75ea58d98a0 +size 3306260832 diff --git a/ChineseErrorCorrector4-4B.imatrix.gguf b/ChineseErrorCorrector4-4B.imatrix.gguf new file mode 100644 index 0000000..c31552d --- /dev/null +++ b/ChineseErrorCorrector4-4B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e526a8094344d19c4f7c97ba881db2c62f86739a986356b3840574de1d5a7b4 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9747a06 --- /dev/null +++ b/README.md @@ -0,0 +1,95 @@ +--- +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 + + + + + + + + + +weighted/imatrix 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-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-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-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChineseErrorCorrector4-4B-i1-GGUF/resolve/main/ChineseErrorCorrector4-4B.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +