commit b543a8bba113ff8bcb249c96cb3a50470684476f Author: ModelHub XC Date: Wed Jun 17 14:50:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/internlm2-20b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0d505d7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +internlm2-20b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-20b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..703be2e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: internlm/internlm2-20b +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/internlm/internlm2-20b + + +static quants are available at https://huggingface.co/mradermacher/internlm2-20b-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/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ1_M.gguf) | i1-IQ1_M | 5.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ2_S.gguf) | i1-IQ2_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ2_M.gguf) | i1-IQ2_M | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q2_K.gguf) | i1-Q2_K | 7.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ3_S.gguf) | i1-IQ3_S | 8.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ3_M.gguf) | i1-IQ3_M | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.9 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q4_0.gguf) | i1-Q4_0 | 11.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-20b-i1-GGUF/resolve/main/internlm2-20b.i1-Q6_K.gguf) | i1-Q6_K | 16.4 | 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..8d5a486 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a56343e1d0022052ded61729936b543df973d56fe7258b0e8c22b502ccd8f85 +size 10234765 diff --git a/internlm2-20b.i1-IQ1_M.gguf b/internlm2-20b.i1-IQ1_M.gguf new file mode 100644 index 0000000..40c8b63 --- /dev/null +++ b/internlm2-20b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4cfb9b5f74e04dc2d7922c0797183af8aaaccfef658d22e1b816878dc9250a +size 4918396736 diff --git a/internlm2-20b.i1-IQ1_S.gguf b/internlm2-20b.i1-IQ1_S.gguf new file mode 100644 index 0000000..a4f6a9a --- /dev/null +++ b/internlm2-20b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:676e3a7188b1a4bd90f91a2f92cbd3843135c0fe08fb93caa999038c1061be52 +size 4543268672 diff --git a/internlm2-20b.i1-IQ2_M.gguf b/internlm2-20b.i1-IQ2_M.gguf new file mode 100644 index 0000000..b3cd1e6 --- /dev/null +++ b/internlm2-20b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576911b772926a4083aec9f02dfab1d342bfcffbfa146827a69588383aa1f516 +size 6974467904 diff --git a/internlm2-20b.i1-IQ2_S.gguf b/internlm2-20b.i1-IQ2_S.gguf new file mode 100644 index 0000000..74737db --- /dev/null +++ b/internlm2-20b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04ddd1fb30fa4ac3b2380c2b3ea3a3e8100b9b35a1dd664184629c8365a4ee2 +size 6474297152 diff --git a/internlm2-20b.i1-IQ2_XS.gguf b/internlm2-20b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..46077ca --- /dev/null +++ b/internlm2-20b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d402d575ca297cfcf827d9c4389e0d3b0b490447499348eec6d45d9b04559107 +size 6100404032 diff --git a/internlm2-20b.i1-IQ2_XXS.gguf b/internlm2-20b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8f9be1a --- /dev/null +++ b/internlm2-20b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79525ce63f38d3cdce62d9edb48fe24a221962aad54d742179ab219c94088194 +size 5543610176 diff --git a/internlm2-20b.i1-IQ3_M.gguf b/internlm2-20b.i1-IQ3_M.gguf new file mode 100644 index 0000000..8260ff4 --- /dev/null +++ b/internlm2-20b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37354699bcdd4d0ebfbcff3e30b9ffbc797b29743e14635da5fdf143c7eacbc2 +size 9121445696 diff --git a/internlm2-20b.i1-IQ3_S.gguf b/internlm2-20b.i1-IQ3_S.gguf new file mode 100644 index 0000000..3154edf --- /dev/null +++ b/internlm2-20b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b0beb5b9b3a12f1846f3cd2dc928e58d65471d707e81405e9990fdc13b04e58 +size 8800581440 diff --git a/internlm2-20b.i1-IQ3_XS.gguf b/internlm2-20b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ad8ec0d --- /dev/null +++ b/internlm2-20b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f28b723b9448d6bec029aee7dba7d1bc75802a80961d1f7257ef488452681b +size 8361752384 diff --git a/internlm2-20b.i1-IQ3_XXS.gguf b/internlm2-20b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..92c97aa --- /dev/null +++ b/internlm2-20b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e7066bf311eb10fd012f67e772a2261df5ab33e1ad07239ba50fff1c3f732a +size 7814377280 diff --git a/internlm2-20b.i1-IQ4_XS.gguf b/internlm2-20b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9573f28 --- /dev/null +++ b/internlm2-20b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e96b47e764fb617a1190a6411defe6d4cd0ca8c3157eb043d043ee74eece60 +size 10766999360 diff --git a/internlm2-20b.i1-Q2_K.gguf b/internlm2-20b.i1-Q2_K.gguf new file mode 100644 index 0000000..af474b9 --- /dev/null +++ b/internlm2-20b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affc74e8d4e64ec2f3ffede9b22f361cc288cb9da2f84a1b8ccf2d3e66ff2e20 +size 7546670912 diff --git a/internlm2-20b.i1-Q3_K_L.gguf b/internlm2-20b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..925853e --- /dev/null +++ b/internlm2-20b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c741669723fc8e6c29584f4d45f86042878c877371cc86e0a3ab750539080761 +size 10551179072 diff --git a/internlm2-20b.i1-Q3_K_M.gguf b/internlm2-20b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..802b880 --- /dev/null +++ b/internlm2-20b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44942069e8a0305e16476c1405f1226d530df66d422dd02bde46954de18fa41a +size 9722279744 diff --git a/internlm2-20b.i1-Q3_K_S.gguf b/internlm2-20b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8f6888d --- /dev/null +++ b/internlm2-20b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8341f286f4404cca687f3955048187827fb0346703505d8add9a7918ee43c2c0 +size 8760473408 diff --git a/internlm2-20b.i1-Q4_0.gguf b/internlm2-20b.i1-Q4_0.gguf new file mode 100644 index 0000000..243c703 --- /dev/null +++ b/internlm2-20b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c0c970fb066f9444f119f97916d18eea80346d0e3d06802a3cf0705a2eccf8 +size 11360436032 diff --git a/internlm2-20b.i1-Q4_K_M.gguf b/internlm2-20b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c527fd8 --- /dev/null +++ b/internlm2-20b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:158849fb0188bdb0ae5901c6ac2bdc5d6e76b1578fd5efe480d9a2efc1e7c57c +size 11984469824 diff --git a/internlm2-20b.i1-Q4_K_S.gguf b/internlm2-20b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b433e40 --- /dev/null +++ b/internlm2-20b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948ce8a90c92ba37701f449ecb4cc0167cafd432d1ff2818ecf694facfe569e8 +size 11401330496 diff --git a/internlm2-20b.i1-Q5_K_M.gguf b/internlm2-20b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d0475d4 --- /dev/null +++ b/internlm2-20b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78bb20aa7bcb1e3605161d26c4ab7162cbfa52fcbeb08c2f9c9ccdcb523d2aee +size 14075100992 diff --git a/internlm2-20b.i1-Q5_K_S.gguf b/internlm2-20b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5b10688 --- /dev/null +++ b/internlm2-20b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960f86ee97c5da408a1becf86e0f33eac0bbe53c3c9cc9c94f35bdcade6f6c64 +size 13734182720 diff --git a/internlm2-20b.i1-Q6_K.gguf b/internlm2-20b.i1-Q6_K.gguf new file mode 100644 index 0000000..1e50b5b --- /dev/null +++ b/internlm2-20b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b843c4e5188a91a036a64e38dcbdb9977e797359da64bf1bb8178699545be924 +size 16296396608