commit ca8d0a43aaa92503084207f402b3818c411278bf Author: ModelHub XC Date: Mon Nov 2 19:56:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gpt-neox-20b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..77bc2e3 --- /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 +gpt-neox-20b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-20b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-neox-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..905195a --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: EleutherAI/gpt-neox-20b +datasets: +- EleutherAI/pile +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- pytorch +- causal-lm +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/EleutherAI/gpt-neox-20b + + +static quants are available at https://huggingface.co/mradermacher/gpt-neox-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/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ1_S.gguf) | i1-IQ1_S | 4.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ1_M.gguf) | i1-IQ1_M | 4.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ2_S.gguf) | i1-IQ2_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ2_M.gguf) | i1-IQ2_M | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q2_K.gguf) | i1-Q2_K | 7.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ3_S.gguf) | i1-IQ3_S | 9.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ3_M.gguf) | i1-IQ3_M | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.1 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q4_0.gguf) | i1-Q4_0 | 11.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.3 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.4 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-neox-20b-i1-GGUF/resolve/main/gpt-neox-20b.i1-Q6_K.gguf) | i1-Q6_K | 17.0 | 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/gpt-neox-20b.i1-IQ1_M.gguf b/gpt-neox-20b.i1-IQ1_M.gguf new file mode 100644 index 0000000..f56497f --- /dev/null +++ b/gpt-neox-20b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abccf28afc6f903a1393a9897554ffe896d239e8b74cec2861888b49ea8df0d +size 4838039552 diff --git a/gpt-neox-20b.i1-IQ1_S.gguf b/gpt-neox-20b.i1-IQ1_S.gguf new file mode 100644 index 0000000..81722c6 --- /dev/null +++ b/gpt-neox-20b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c02fc5f18102a1ee61234c0237a2124a4d1658b83c57c231e956968527e8971 +size 4427522048 diff --git a/gpt-neox-20b.i1-IQ2_M.gguf b/gpt-neox-20b.i1-IQ2_M.gguf new file mode 100644 index 0000000..2780c7b --- /dev/null +++ b/gpt-neox-20b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81cd22b93921c6afbcefdf932b01ab0cde9689452abc358f045db9645b570e1 +size 7010570240 diff --git a/gpt-neox-20b.i1-IQ2_S.gguf b/gpt-neox-20b.i1-IQ2_S.gguf new file mode 100644 index 0000000..e241188 --- /dev/null +++ b/gpt-neox-20b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3fb5f6508569793df79c59ec532667164681d600935c2d44e37471a1ad89975 +size 6463213568 diff --git a/gpt-neox-20b.i1-IQ2_XS.gguf b/gpt-neox-20b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..dfae704 --- /dev/null +++ b/gpt-neox-20b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a0177d41e1b9821255f09ed6dc62e895882ef941aa77e7e1d1862689b261a7a +size 6121496576 diff --git a/gpt-neox-20b.i1-IQ2_XXS.gguf b/gpt-neox-20b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..29f375a --- /dev/null +++ b/gpt-neox-20b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3595dae71cccbf177a462dcffa6ef31b4561680c57089a29a64e91ad6d23387c +size 5522235392 diff --git a/gpt-neox-20b.i1-IQ3_M.gguf b/gpt-neox-20b.i1-IQ3_M.gguf new file mode 100644 index 0000000..bf81c81 --- /dev/null +++ b/gpt-neox-20b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a93ad3dc4c9e5646df689109b0ce411705044503c15a76019a6f623a7718602d +size 9950117888 diff --git a/gpt-neox-20b.i1-IQ3_S.gguf b/gpt-neox-20b.i1-IQ3_S.gguf new file mode 100644 index 0000000..b09118b --- /dev/null +++ b/gpt-neox-20b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d32fe1f04070740c4bd345aa5e4ddd381abec366d95510be7b20eb3ebe2652b +size 8967471104 diff --git a/gpt-neox-20b.i1-IQ3_XS.gguf b/gpt-neox-20b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..92577d9 --- /dev/null +++ b/gpt-neox-20b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fc37ea2407a7c530cf71bb5c5e44b50b6711d164e50c6c964ee8edab1aafc0 +size 8733900800 diff --git a/gpt-neox-20b.i1-IQ3_XXS.gguf b/gpt-neox-20b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..46b72f5 --- /dev/null +++ b/gpt-neox-20b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be4335ae42207e1202de37fb888f082411d70bcbce2e3e137747922b443903d +size 8069894144 diff --git a/gpt-neox-20b.i1-IQ4_XS.gguf b/gpt-neox-20b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..57af9bd --- /dev/null +++ b/gpt-neox-20b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0076de53b796f6613a2dfcf2d7c8c53f55d33d5b88075164faf8b09fdc8f6667 +size 11023216640 diff --git a/gpt-neox-20b.i1-Q2_K.gguf b/gpt-neox-20b.i1-Q2_K.gguf new file mode 100644 index 0000000..6621b64 --- /dev/null +++ b/gpt-neox-20b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236c31c2d5cb393c13eca1a0a058717f7accfc1d4dbc434ca13088db3ea5be55 +size 7755173888 diff --git a/gpt-neox-20b.i1-Q3_K_L.gguf b/gpt-neox-20b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6f5456b --- /dev/null +++ b/gpt-neox-20b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa41ab675ed72e21a8d9fe1c2beaf1ad8de8dd1bbb9ffcf5f7fb31fde4f87dc +size 11770314752 diff --git a/gpt-neox-20b.i1-Q3_K_M.gguf b/gpt-neox-20b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1bf951c --- /dev/null +++ b/gpt-neox-20b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97083350aa48f6cc23e540f49e205b189b1f58508ca0573b160b01345e73cd36 +size 10769973248 diff --git a/gpt-neox-20b.i1-Q3_K_S.gguf b/gpt-neox-20b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a8b7f05 --- /dev/null +++ b/gpt-neox-20b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227632ac178bd87e0601cc073f162d5d09e0c68eb341c404138117781bfc51cb +size 8967471104 diff --git a/gpt-neox-20b.i1-Q4_0.gguf b/gpt-neox-20b.i1-Q4_0.gguf new file mode 100644 index 0000000..49f1037 --- /dev/null +++ b/gpt-neox-20b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c780c9ac74af46c7231d6a87ed0f0ef9e6cb2d19be89efb9a36138085b8acd30 +size 11702939648 diff --git a/gpt-neox-20b.i1-Q4_K_M.gguf b/gpt-neox-20b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3dbd9e0 --- /dev/null +++ b/gpt-neox-20b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a35c13535c26bb925a2379d9f021de67a0390124ffe2051aa94412002652d6d +size 13135032320 diff --git a/gpt-neox-20b.i1-Q4_K_S.gguf b/gpt-neox-20b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..aa09259 --- /dev/null +++ b/gpt-neox-20b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582b2c8edf9723917996bcd0f6c5840140e39a20e92b6f573d698d0519a2c81e +size 11750125568 diff --git a/gpt-neox-20b.i1-Q5_K_M.gguf b/gpt-neox-20b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ccf9d3e --- /dev/null +++ b/gpt-neox-20b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b5352761cc77e43db384884ab8a4b8d5d5bfa271ec86888d284cd26008adb1 +size 15288872960 diff --git a/gpt-neox-20b.i1-Q5_K_S.gguf b/gpt-neox-20b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9536e40 --- /dev/null +++ b/gpt-neox-20b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a06fde0b0b5132fa37a82146cf51f6147c6cd7df6d53ea0aa94398d1b246c92 +size 14185902080 diff --git a/gpt-neox-20b.i1-Q6_K.gguf b/gpt-neox-20b.i1-Q6_K.gguf new file mode 100644 index 0000000..7a0bff0 --- /dev/null +++ b/gpt-neox-20b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1ce8714bab3bd37cce47314b1a03ef6371f305ad7db720f98deaf170fcfa34 +size 16874184704 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..d9412b7 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23676c48e4526bc2ddfcbea7c9122af17d7642931b35a8839218c381978769fe +size 7575431