commit d05401745056414039a9f0ca3211284fe18943e1 Author: ModelHub XC Date: Fri Jun 19 09:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/internlm2_5-20b-chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d0e969 --- /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_5-20b-chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-20b-chat.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..038d903 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: internlm/internlm2_5-20b-chat +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/internlm/internlm2_5-20b-chat + + +static quants are available at https://huggingface.co/mradermacher/internlm2_5-20b-chat-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_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ1_M.gguf) | i1-IQ1_M | 5.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ2_S.gguf) | i1-IQ2_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ2_M.gguf) | i1-IQ2_M | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q2_K.gguf) | i1-Q2_K | 7.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ3_S.gguf) | i1-IQ3_S | 8.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ3_M.gguf) | i1-IQ3_M | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.9 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q4_0.gguf) | i1-Q4_0 | 11.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-20b-chat-i1-GGUF/resolve/main/internlm2_5-20b-chat.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..a65ae3a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d3a60253e2f9c2916ce98d6321d6e3072e2c8d95508879ca2ede2757de428d +size 10234765 diff --git a/internlm2_5-20b-chat.i1-IQ1_M.gguf b/internlm2_5-20b-chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..16966d7 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6e877bc774365d1c4b51ceab45e3a8ed62a4bc783205400758e27f3e02b317 +size 4918397120 diff --git a/internlm2_5-20b-chat.i1-IQ1_S.gguf b/internlm2_5-20b-chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..e4ee856 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b249a844a9b57fe617cb616c448365f9ef9bb5de8c77b11057543dda0055a0f +size 4543269056 diff --git a/internlm2_5-20b-chat.i1-IQ2_M.gguf b/internlm2_5-20b-chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..407843e --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd29869073bbc9392e6d59e90fc7eb6598105fb7a360f1d99b367e96499e7b5 +size 6974468288 diff --git a/internlm2_5-20b-chat.i1-IQ2_S.gguf b/internlm2_5-20b-chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..43f1bf8 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba09b0b3bc7062e968550792025ca58258652bdf7efedb7842d288fe67f8c8b7 +size 6474297536 diff --git a/internlm2_5-20b-chat.i1-IQ2_XS.gguf b/internlm2_5-20b-chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1de1db1 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e3ae375c6f658cd08277d753a35ff9e50c9698ca3e249bc2531dc0170f5672e +size 6100404416 diff --git a/internlm2_5-20b-chat.i1-IQ2_XXS.gguf b/internlm2_5-20b-chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2195f13 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca27ca54bc1d5d212d4f72e9525f8c093bd2dcb36a605aac06acf9ad122c9370 +size 5543610560 diff --git a/internlm2_5-20b-chat.i1-IQ3_M.gguf b/internlm2_5-20b-chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..a8fcab2 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ff9e377bac405e110006089656cbb5729a3221a19e1283f01fc1a6ab258ad0 +size 9121446080 diff --git a/internlm2_5-20b-chat.i1-IQ3_S.gguf b/internlm2_5-20b-chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..7166a2b --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6581bc1c00e59aa1fdcf8ce29ab5bc860fe5eb4baeaac711f2847084fef4689 +size 8800581824 diff --git a/internlm2_5-20b-chat.i1-IQ3_XS.gguf b/internlm2_5-20b-chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..99efb10 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492cdf518c1c9dcfa819a001f6ce2a44b85a9f4aec42f3e4693604efacc16883 +size 8361752768 diff --git a/internlm2_5-20b-chat.i1-IQ3_XXS.gguf b/internlm2_5-20b-chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d0a3eff --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e83580ed2b604627f86fa2c7d0e58c05ead31fc9a9d2b065817f57e3356b636 +size 7814377664 diff --git a/internlm2_5-20b-chat.i1-IQ4_XS.gguf b/internlm2_5-20b-chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..44141f5 --- /dev/null +++ b/internlm2_5-20b-chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa46555cdb124480c751a1cad353ff926f66be22d9d4313193ffba8478ece082 +size 10766999744 diff --git a/internlm2_5-20b-chat.i1-Q2_K.gguf b/internlm2_5-20b-chat.i1-Q2_K.gguf new file mode 100644 index 0000000..8c659d0 --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a816e46080923caa97f78c26b964dd6263a084243dcf609f3eff58eca13bbe06 +size 7546671296 diff --git a/internlm2_5-20b-chat.i1-Q3_K_L.gguf b/internlm2_5-20b-chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5c29bc6 --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ca0ec99dd0c405e6c5b33b5d4d99a9510e4ada6f3b06172cfcb6c5fc16513b +size 10551179456 diff --git a/internlm2_5-20b-chat.i1-Q3_K_M.gguf b/internlm2_5-20b-chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2ffa19e --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2531864033723277a5b513b03a84c6389060da1cf5d87e4f1cbd4b0e4b9c2b87 +size 9722280128 diff --git a/internlm2_5-20b-chat.i1-Q3_K_S.gguf b/internlm2_5-20b-chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..acfd6ae --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827944ac3f017ba52cc587f46cef8e534955b5a19bb167e85984af0186b49e5d +size 8760473792 diff --git a/internlm2_5-20b-chat.i1-Q4_0.gguf b/internlm2_5-20b-chat.i1-Q4_0.gguf new file mode 100644 index 0000000..d96d90e --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea4d0c0f1b1edd233708c5f12edd8b1eef005be338a04ace2268bec27228de1 +size 11360436416 diff --git a/internlm2_5-20b-chat.i1-Q4_K_M.gguf b/internlm2_5-20b-chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5293661 --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826dfc225cd0f32140d13774fa64c3e285bc2c5aacf2dd6d3647806191b297ca +size 11984470208 diff --git a/internlm2_5-20b-chat.i1-Q4_K_S.gguf b/internlm2_5-20b-chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e0297f6 --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e7c451458567097f8975bf7d7179fabeb2ee0a487799b325fcd26bf70db3d9 +size 11401330880 diff --git a/internlm2_5-20b-chat.i1-Q5_K_M.gguf b/internlm2_5-20b-chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..65710cb --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f6d078cd065c08a3e1f210271c406b35ce0ecdf6bd01d8b8dad2617733e540 +size 14075101376 diff --git a/internlm2_5-20b-chat.i1-Q5_K_S.gguf b/internlm2_5-20b-chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e2e703a --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607531f3700dc8aa2bfe1e3417eaa95c976343c4fe93add6e9bac8d07abfc489 +size 13734183104 diff --git a/internlm2_5-20b-chat.i1-Q6_K.gguf b/internlm2_5-20b-chat.i1-Q6_K.gguf new file mode 100644 index 0000000..1fdf7d6 --- /dev/null +++ b/internlm2_5-20b-chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0c3d11a8cf14cc5821a0893ee0da1cafff870ac8bab51bbfd1c17806cbc917 +size 16296396992