commit 09def9188fe40daf366628565cf90633d8c7c6a9 Author: ModelHub XC Date: Sat Jun 20 10:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/internlm2-math-20b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f40bc5c --- /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-math-20b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-20b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2-math-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..3bd46f8 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: internlm/internlm2-math-20b +language: +- en +- zh +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- math +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/internlm/internlm2-math-20b + + +static quants are available at https://huggingface.co/mradermacher/internlm2-math-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-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ1_M.gguf) | i1-IQ1_M | 5.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ2_S.gguf) | i1-IQ2_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ2_M.gguf) | i1-IQ2_M | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q2_K.gguf) | i1-Q2_K | 7.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ3_S.gguf) | i1-IQ3_S | 8.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ3_M.gguf) | i1-IQ3_M | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.9 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q4_0.gguf) | i1-Q4_0 | 11.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-20b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2-math-20b-i1-GGUF/resolve/main/internlm2-math-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..399df49 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8988a13ec868b14839a83db84a3825690f18819d5eaf1be8483313ec45d033 +size 10234765 diff --git a/internlm2-math-20b.i1-IQ1_M.gguf b/internlm2-math-20b.i1-IQ1_M.gguf new file mode 100644 index 0000000..06932f2 --- /dev/null +++ b/internlm2-math-20b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405dc04c0a9f1e37df3beff75188cc2fa759d11d48ab28f5f91d7a61ae596965 +size 4918397056 diff --git a/internlm2-math-20b.i1-IQ1_S.gguf b/internlm2-math-20b.i1-IQ1_S.gguf new file mode 100644 index 0000000..3ba8ff8 --- /dev/null +++ b/internlm2-math-20b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e85cc6e2302e03fca3947ba637edf47aff28548a100fee526352a66f9cf6dd6 +size 4543268992 diff --git a/internlm2-math-20b.i1-IQ2_M.gguf b/internlm2-math-20b.i1-IQ2_M.gguf new file mode 100644 index 0000000..9e9969c --- /dev/null +++ b/internlm2-math-20b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1dce09b2059701837f29bc80d74cc39b431c77113d71a251df6f93d6edfe03a +size 6974468224 diff --git a/internlm2-math-20b.i1-IQ2_S.gguf b/internlm2-math-20b.i1-IQ2_S.gguf new file mode 100644 index 0000000..e224139 --- /dev/null +++ b/internlm2-math-20b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2978f9d0eb75c33c6511a663e5eee64a55e2e429a3ca08da6edc10f3990c9c +size 6474297472 diff --git a/internlm2-math-20b.i1-IQ2_XS.gguf b/internlm2-math-20b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fe8bfc7 --- /dev/null +++ b/internlm2-math-20b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd11c9ec7891afb8e2a851fa19be47835391ab1b487e298a01ca89ac1b21bb6 +size 6100404352 diff --git a/internlm2-math-20b.i1-IQ2_XXS.gguf b/internlm2-math-20b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1546fef --- /dev/null +++ b/internlm2-math-20b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dcf7a5704250a28bbb4f084686b60de6952a954c519f40336f0e90df864d87b +size 5543610496 diff --git a/internlm2-math-20b.i1-IQ3_M.gguf b/internlm2-math-20b.i1-IQ3_M.gguf new file mode 100644 index 0000000..2d40fe7 --- /dev/null +++ b/internlm2-math-20b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d871d581852378e8ea83e2709f7d3343d12528721cee9a2ec8b490abd5a416 +size 9121446016 diff --git a/internlm2-math-20b.i1-IQ3_S.gguf b/internlm2-math-20b.i1-IQ3_S.gguf new file mode 100644 index 0000000..b03c51b --- /dev/null +++ b/internlm2-math-20b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b890cf0797d9800535a5833694284ac5f26860c4f2263cc68b2367f84969da65 +size 8800581760 diff --git a/internlm2-math-20b.i1-IQ3_XS.gguf b/internlm2-math-20b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..752cacd --- /dev/null +++ b/internlm2-math-20b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8ba93a5bcc2bf528aeb3964a1e66403dc4868c435e2ab28dc148409ee44fe7 +size 8361752704 diff --git a/internlm2-math-20b.i1-IQ3_XXS.gguf b/internlm2-math-20b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8a36fd4 --- /dev/null +++ b/internlm2-math-20b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49becedf4f69ed7067af785a9d75df013c9639cd3249b9a5e36db7513f3e6fbf +size 7814377600 diff --git a/internlm2-math-20b.i1-IQ4_XS.gguf b/internlm2-math-20b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e53e285 --- /dev/null +++ b/internlm2-math-20b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce72c6147ddc78dd23963ed344ffe37f934746f98794ca324e28c2256eda41ac +size 10766999680 diff --git a/internlm2-math-20b.i1-Q2_K.gguf b/internlm2-math-20b.i1-Q2_K.gguf new file mode 100644 index 0000000..523d396 --- /dev/null +++ b/internlm2-math-20b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a75c1da5b8ce8f950fb464f5e5b6c077aa9733c19dbb47831ccf696ad812363 +size 7546671232 diff --git a/internlm2-math-20b.i1-Q3_K_L.gguf b/internlm2-math-20b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d683835 --- /dev/null +++ b/internlm2-math-20b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2549f45a88eacfe09cb7c31877d87d63511c26d384d7eb84b7f7b8472fe55bce +size 10551179392 diff --git a/internlm2-math-20b.i1-Q3_K_M.gguf b/internlm2-math-20b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..42adec8 --- /dev/null +++ b/internlm2-math-20b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d7ea1f1af4f688d6a2c03f8c1f9d2da0ee42e024305b12169ad24e21596200 +size 9722280064 diff --git a/internlm2-math-20b.i1-Q3_K_S.gguf b/internlm2-math-20b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..54a53ae --- /dev/null +++ b/internlm2-math-20b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328fb3f4e8aef2a4819dedd9b61d5117b13b15e0effbf15165b3285ee435117a +size 8760473728 diff --git a/internlm2-math-20b.i1-Q4_0.gguf b/internlm2-math-20b.i1-Q4_0.gguf new file mode 100644 index 0000000..51e4401 --- /dev/null +++ b/internlm2-math-20b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63c9575cf7faa611f55da1f2386a4e03de0c4789708dc30d06b6e62c3b2fc09 +size 11360436352 diff --git a/internlm2-math-20b.i1-Q4_K_M.gguf b/internlm2-math-20b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a41a020 --- /dev/null +++ b/internlm2-math-20b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc97dad5e28f8b4bd2bb79a183990a07903b5def677ea1ce0d7a7223767f4d7 +size 11984470144 diff --git a/internlm2-math-20b.i1-Q4_K_S.gguf b/internlm2-math-20b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f63c791 --- /dev/null +++ b/internlm2-math-20b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d118e3422465eaa364a4489cb062549cc7281e39896f27bbc707561176e22ebe +size 11401330816 diff --git a/internlm2-math-20b.i1-Q5_K_M.gguf b/internlm2-math-20b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..22e288e --- /dev/null +++ b/internlm2-math-20b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d88bff91c118b8b5168f7447b7f2601e942b01070ec6b464dbf7bf78f1aa83 +size 14075101312 diff --git a/internlm2-math-20b.i1-Q5_K_S.gguf b/internlm2-math-20b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e73229b --- /dev/null +++ b/internlm2-math-20b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd6d885aefee2a6eaf69d6cafd1969d3d41cef0346d956744ff76732f78c5d6 +size 13734183040 diff --git a/internlm2-math-20b.i1-Q6_K.gguf b/internlm2-math-20b.i1-Q6_K.gguf new file mode 100644 index 0000000..5ec565d --- /dev/null +++ b/internlm2-math-20b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc8e5ab947f2c6a9eb115bca657bc885b72f2f03187aae5955a17cc3f1ae07f +size 16296396928