commit 8c855883f1e4863977b77d398099ea98725f1df7 Author: ModelHub XC Date: Thu May 14 18:07:40 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bfd6978 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KwaiCoder-23B-A4B-v1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf new file mode 100644 index 0000000..88a973c --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3062f0b36b99d5bc25f665724590add5b94bb0e47a655f59548b68c497d303 +size 7792717856 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ1_S.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ1_S.gguf new file mode 100644 index 0000000..3b9975f --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d256c83d18edcbc763c08571c3233f96741e3274fc9e5b175053d905e7aa73 +size 7438823456 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf new file mode 100644 index 0000000..e079714 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ea78c6dcc7a3b99020ad10f0d41fb8be641ef10a64232acf27cb98c119510f +size 9397297184 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ2_S.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ2_S.gguf new file mode 100644 index 0000000..709dad5 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647e0ac7c61396deb9423eac239fd9b5b6e384adb41036fbc449c444e8567ecf +size 8925437984 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ2_XS.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6e8bb15 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d641fe92930cd8eb7c1091ac41f38d26521f5b7d0c1a86a8d2b80067c677e803 +size 8864886816 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d3aec2e --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b64ad7057fdd5b9925cfa5495d35045b86b008336c2957ce204be464bcf3700 +size 8382541856 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf new file mode 100644 index 0000000..38dc23d --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc7e7b49005b3f4720f160569aa66c099ce495f6f88f72e912cb8e1abb96d88 +size 11201024032 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ3_S.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ3_S.gguf new file mode 100644 index 0000000..e34e96e --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f48caea4b44d4ebe1c790cf0e212344d4263b74bc1d6115ee3ebbcf267f2fc +size 11021717536 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ3_XS.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..464a2a0 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715c89bc6dcf8babe3670e249a026fe1defff152ad371d77f64c44bb0805b49c +size 10483011616 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..17f61c4 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c287d8e37f7668297cf907186209f9775f89196bf80a8bc138153c3994a2954f +size 10238779424 diff --git a/KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf b/KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..31a85e9 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60eb9f7c0488426fa6be7b8736065a8bf52c6783c76d669793581c7f8e7d85ef +size 12636782624 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf b/KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf new file mode 100644 index 0000000..6b05bd1 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c23080d5c9284ce1e1c7339fe4b6f33fbb5d9e486ff1a66fb73d02c278680f +size 9474809888 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf b/KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..67c6be9 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830fddf57cf0ec1b4db907389e9f49058f9cd804add19d301e3b2c6a35b08b82 +size 9496829984 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf b/KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4ad81a8 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01e2e57d3d287db78f86c171d499fee1cbb880c2870aa97709232577d792cdd +size 12547395616 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf b/KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e0fcbf4 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53797286f7cbc5915847abac5f013510359e42a125d3ce6c87557ef80a87c06e +size 12039360544 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf b/KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..50973b6 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b8ec1ec5af8c460c81a7ee525e347301318e1e445ac4a43c5a93244c4b00288 +size 11021717536 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q4_0.gguf b/KwaiCoder-23B-A4B-v1.i1-Q4_0.gguf new file mode 100644 index 0000000..e5deb9e --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba107baa73bc6d7e5f4a07e1b0f6d676c3312dc7c0247ce05bb1899ef30f034 +size 13178814496 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q4_1.gguf b/KwaiCoder-23B-A4B-v1.i1-Q4_1.gguf new file mode 100644 index 0000000..ae7229b --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd12e943825adbdf3047e3a7f88d13456c7a5f022dbd0486e5c867537e6a5741 +size 14578499616 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf b/KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5c7ac4c --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b0f7bd35d567cd7b539293cc3ea0f823a1d241c413f34832b7bdc653b17dd8e +size 15431417888 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf b/KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a1efb52 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4555fdd5da844fd8043e6e62a1c49f7bd55c117c21cc1d0dbf97451dac6e0b11 +size 14088978464 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q5_K_M.gguf b/KwaiCoder-23B-A4B-v1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..683c029 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4b27ecb9f01ab64acb09487e38c6c1c19165d2820b45ba01e5527224bd3425 +size 17623662624 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q5_K_S.gguf b/KwaiCoder-23B-A4B-v1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f868b95 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a485c23b77cf187357bdd3a206a24fd172b6d17e5aa5f82f89e6223c1888214a +size 16474161184 diff --git a/KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf b/KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf new file mode 100644 index 0000000..9d2f6c0 --- /dev/null +++ b/KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cde7dea3a6a9d44f94ccd85ea86a72019177a5984bfe269aefc4d1ab9674b38 +size 20840607776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..23267da --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Kwaipilot/KwaiCoder-23B-A4B-v1 +language: +- multilingual +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- code-generation +- transformers +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Kwaipilot/KwaiCoder-23B-A4B-v1 + + +static quants are available at https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-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/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 7.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 7.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.0 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 9.0 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf) | i1-Q2_K | 9.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 11.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 11.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 11.3 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.7 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_0.gguf) | i1-Q4_0 | 13.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_1.gguf) | i1-Q4_1 | 14.7 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.6 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.7 | | +| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf) | i1-Q6_K | 20.9 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..8a62cd5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0f394a66779c63425a323b8eeb16ccd1cab14b53d86e26c04ca2936135a427 +size 50632235