commit 6a41712b93883281471a71c9633d4304d5ef198c Author: ModelHub XC Date: Fri May 8 23:58:49 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b8171b7 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-4.5-0.3B-PT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ1_M.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ1_M.gguf new file mode 100644 index 0000000..9749b7b --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d6f471b89043e746c8ed17fd55a711d6693a9cb76f3451ce08957d6bb0073e +size 134868704 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ1_S.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ1_S.gguf new file mode 100644 index 0000000..bc807d8 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886265c3bba07a15e5c943e23b9754dc3b2cfa2aed1755b7fee4e4b47a83a060 +size 130039520 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ2_M.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ2_M.gguf new file mode 100644 index 0000000..fad0535 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0344592e7ffacd4e0b5149376dfdc2500817674050c077c9118387ebce370d6 +size 162922208 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ2_S.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ2_S.gguf new file mode 100644 index 0000000..401ad6f --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19bf49123f0dd4e99e28671b910450fe649552e67dadbc3f06429a3e16af59e2 +size 156483296 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ2_XS.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8df5569 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e7d0132d28d8cfc49347a5b21cd66b5eabe21c1af54812f92d00fc2982cd9b +size 150535904 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ2_XXS.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..dfcd6b7 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82528b27651dcfc5a8a262641c5b4d11e9511787111773116527e4b9c7efebd +size 142917344 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ3_M.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ3_M.gguf new file mode 100644 index 0000000..36c6b04 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69614a4155a7b67fae1fdcc6b80172bfa9dc7113549b7446765fa6cc799b429b +size 205373152 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ3_S.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ3_S.gguf new file mode 100644 index 0000000..182665b --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa093bcc204674fa2087410d3a0916577bf93877d506b0696b066e84c7f6867 +size 199524064 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ3_XS.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ea4e9c4 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc2d55a06c88ebf14eb9ee68a9752e9df93d21e5106a8640db97ef1be59e9ed8 +size 193699552 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ3_XXS.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..99535ae --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ea755aa98e57037c58477d4cc8352f21d730b8a7a3293c210d94c5021ce2d2 +size 172850912 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ4_NL.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ad61b06 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005697842baf9f611566affd17723fa789adf5a02560fd1771cb332e23f736f2 +size 233328352 diff --git a/ERNIE-4.5-0.3B-PT.i1-IQ4_XS.gguf b/ERNIE-4.5-0.3B-PT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..85456c0 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1878206f1321ba00e604a7b27baee2eff2fba09b26c64debefd9cd0d5314e7b5 +size 225513184 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q2_K.gguf b/ERNIE-4.5-0.3B-PT.i1-Q2_K.gguf new file mode 100644 index 0000000..b0b1063 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197c4f046f7a8338cb282c2b8dd8313e61359c007da81dff364152924d52b7e6 +size 183709408 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q2_K_S.gguf b/ERNIE-4.5-0.3B-PT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..edd9d9c --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78040a6d0fc175c15de78487cd2ddc8527e2f31c4169572f116393151ceb4bbe +size 175599328 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q3_K_L.gguf b/ERNIE-4.5-0.3B-PT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..68b7225 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acc826d1a836ddb5b7220440cfefa9de1438e621764b0da3d602b1b1c90ef98 +size 224444128 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q3_K_M.gguf b/ERNIE-4.5-0.3B-PT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..12d5f2a --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ed5da4a06d5deba59b325fecff69b33202e5044bab9bf57442ecdb3f2d4242 +size 212516576 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q3_K_S.gguf b/ERNIE-4.5-0.3B-PT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4fdd6c8 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36f20d6caa989c7150d9952f7ca12be798d9da4ba02ab20ae2d6aae4d0402c86 +size 198897376 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q4_0.gguf b/ERNIE-4.5-0.3B-PT.i1-Q4_0.gguf new file mode 100644 index 0000000..82bbdaf --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0312128fa14f6a16406414ee3d9a1ffa87ca101decddc8c30c38b4ebbb5506f5 +size 233131744 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q4_1.gguf b/ERNIE-4.5-0.3B-PT.i1-Q4_1.gguf new file mode 100644 index 0000000..94d839d --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae913556ea462762a1d66270e0b617894f8c81fb52eb4acd8c2880a907cda00 +size 248663776 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q4_K_M.gguf b/ERNIE-4.5-0.3B-PT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f83bd2e --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba832e6f40761fefaee342c438a083e77a09e8658ff8affba97bf35cacc19a4 +size 240645856 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q4_K_S.gguf b/ERNIE-4.5-0.3B-PT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..323d68a --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82bd2c4ff9a2a306abae501cb8e85688aa580538eef42e839e86621c7c185641 +size 233656032 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q5_K_M.gguf b/ERNIE-4.5-0.3B-PT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..01d0eee --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d884924300f2791dcbb4589cafa70a159e9e3c57016d39e11c7ce9fd2f3fdef +size 268662496 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q5_K_S.gguf b/ERNIE-4.5-0.3B-PT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7490fd1 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:274a3a2c1c66f6ee0ce5add39f578db9affadc94e8cdb7182baf10e5ff1fa77c +size 264589024 diff --git a/ERNIE-4.5-0.3B-PT.i1-Q6_K.gguf b/ERNIE-4.5-0.3B-PT.i1-Q6_K.gguf new file mode 100644 index 0000000..9cd5e76 --- /dev/null +++ b/ERNIE-4.5-0.3B-PT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bcbc17e07cba47232acbffc088db18f082891caa84b80b67a542e3d761d7c50 +size 298430176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a931fb --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: baidu/ERNIE-4.5-0.3B-PT +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ERNIE4.5 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ERNIE-4.5-0.3B-PT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-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/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ1_S.gguf) | i1-IQ1_S | 0.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ1_M.gguf) | i1-IQ1_M | 0.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ2_S.gguf) | i1-IQ2_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ2_M.gguf) | i1-IQ2_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q2_K.gguf) | i1-Q2_K | 0.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ3_S.gguf) | i1-IQ3_S | 0.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ3_M.gguf) | i1-IQ3_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q4_0.gguf) | i1-Q4_0 | 0.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q4_1.gguf) | i1-Q4_1 | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-4.5-0.3B-PT-i1-GGUF/resolve/main/ERNIE-4.5-0.3B-PT.i1-Q6_K.gguf) | i1-Q6_K | 0.4 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..aa7fce4 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c8e934387806f176b1e6760e9516febda090803c4d7ba56467bc0eef85858e7 +size 741439