From c66adc73d0e87e2c62f7a9dba9b7cc93eab21bf0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 19 Apr 2026 11:51:28 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/openchatgpt-neox-125m-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++++++ README.md | 87 +++++++++++++++++++++++++++ imatrix.dat | 3 + openchatgpt-neox-125m.i1-IQ1_M.gguf | 3 + openchatgpt-neox-125m.i1-IQ1_S.gguf | 3 + openchatgpt-neox-125m.i1-IQ2_M.gguf | 3 + openchatgpt-neox-125m.i1-IQ2_S.gguf | 3 + openchatgpt-neox-125m.i1-IQ2_XS.gguf | 3 + openchatgpt-neox-125m.i1-IQ2_XXS.gguf | 3 + openchatgpt-neox-125m.i1-IQ3_M.gguf | 3 + openchatgpt-neox-125m.i1-IQ3_S.gguf | 3 + openchatgpt-neox-125m.i1-IQ3_XS.gguf | 3 + openchatgpt-neox-125m.i1-IQ3_XXS.gguf | 3 + openchatgpt-neox-125m.i1-IQ4_NL.gguf | 3 + openchatgpt-neox-125m.i1-IQ4_XS.gguf | 3 + openchatgpt-neox-125m.i1-Q2_K.gguf | 3 + openchatgpt-neox-125m.i1-Q2_K_S.gguf | 3 + openchatgpt-neox-125m.i1-Q3_K_L.gguf | 3 + openchatgpt-neox-125m.i1-Q3_K_M.gguf | 3 + openchatgpt-neox-125m.i1-Q3_K_S.gguf | 3 + openchatgpt-neox-125m.i1-Q4_0.gguf | 3 + openchatgpt-neox-125m.i1-Q4_1.gguf | 3 + openchatgpt-neox-125m.i1-Q4_K_M.gguf | 3 + openchatgpt-neox-125m.i1-Q4_K_S.gguf | 3 + openchatgpt-neox-125m.i1-Q5_K_M.gguf | 3 + openchatgpt-neox-125m.i1-Q5_K_S.gguf | 3 + openchatgpt-neox-125m.i1-Q6_K.gguf | 3 + 27 files changed, 222 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 openchatgpt-neox-125m.i1-IQ1_M.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ1_S.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ2_M.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ2_S.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ2_XS.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ2_XXS.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ3_M.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ3_S.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ3_XS.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ3_XXS.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ4_NL.gguf create mode 100644 openchatgpt-neox-125m.i1-IQ4_XS.gguf create mode 100644 openchatgpt-neox-125m.i1-Q2_K.gguf create mode 100644 openchatgpt-neox-125m.i1-Q2_K_S.gguf create mode 100644 openchatgpt-neox-125m.i1-Q3_K_L.gguf create mode 100644 openchatgpt-neox-125m.i1-Q3_K_M.gguf create mode 100644 openchatgpt-neox-125m.i1-Q3_K_S.gguf create mode 100644 openchatgpt-neox-125m.i1-Q4_0.gguf create mode 100644 openchatgpt-neox-125m.i1-Q4_1.gguf create mode 100644 openchatgpt-neox-125m.i1-Q4_K_M.gguf create mode 100644 openchatgpt-neox-125m.i1-Q4_K_S.gguf create mode 100644 openchatgpt-neox-125m.i1-Q5_K_M.gguf create mode 100644 openchatgpt-neox-125m.i1-Q5_K_S.gguf create mode 100644 openchatgpt-neox-125m.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..13ff32a --- /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 +openchatgpt-neox-125m.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4d29e94 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: mrsteyk/openchatgpt-neox-125m +language: +- en +library_name: transformers +license: +- creativeml-openrail-m +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- text generation +- pytorch +- casual-lm +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mrsteyk/openchatgpt-neox-125m + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#openchatgpt-neox-125m-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/openchatgpt-neox-125m-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/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ1_S.gguf) | i1-IQ1_S | 0.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ1_M.gguf) | i1-IQ1_M | 0.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ2_S.gguf) | i1-IQ2_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ2_M.gguf) | i1-IQ2_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q2_K.gguf) | i1-Q2_K | 0.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ3_S.gguf) | i1-IQ3_S | 0.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ3_M.gguf) | i1-IQ3_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q4_0.gguf) | i1-Q4_0 | 0.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q4_1.gguf) | i1-Q4_1 | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-i1-GGUF/resolve/main/openchatgpt-neox-125m.i1-Q6_K.gguf) | i1-Q6_K | 0.2 | 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..62c2644 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0e4893df3839a073c543eac1532a02523a133f26128d31972208858862583b +size 259687 diff --git a/openchatgpt-neox-125m.i1-IQ1_M.gguf b/openchatgpt-neox-125m.i1-IQ1_M.gguf new file mode 100644 index 0000000..64a3d92 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d746befb1519f6514bf818af6a772904dc38c42a69780b0b6c42c91c91d01b01 +size 60593696 diff --git a/openchatgpt-neox-125m.i1-IQ1_S.gguf b/openchatgpt-neox-125m.i1-IQ1_S.gguf new file mode 100644 index 0000000..f48824c --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae1b9e76df74675d2bf4b4e0f280ef77bb54144ce9cf0a2617b79b465e9f817 +size 58824224 diff --git a/openchatgpt-neox-125m.i1-IQ2_M.gguf b/openchatgpt-neox-125m.i1-IQ2_M.gguf new file mode 100644 index 0000000..cf847e9 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a313f32ef9e660197edcf2062e33c63c250b3fc70decb4952b6f699f4b7f3eb7 +size 73639200 diff --git a/openchatgpt-neox-125m.i1-IQ2_S.gguf b/openchatgpt-neox-125m.i1-IQ2_S.gguf new file mode 100644 index 0000000..bd54e98 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2650a4fe85b198a3fb0b3e4f9e6f149b65364c27e7d23ef67641b047539d5aad +size 71279904 diff --git a/openchatgpt-neox-125m.i1-IQ2_XS.gguf b/openchatgpt-neox-125m.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6c9254b --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767c29e6a0e4746327a3ae81b66c17837c7e45c225263f8e2ef6734638773833 +size 66123296 diff --git a/openchatgpt-neox-125m.i1-IQ2_XXS.gguf b/openchatgpt-neox-125m.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6f18f5c --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a25b5eac17d4b2bd7bf4af072ae73abd4a469d1f9e5dc46929f06d35c6709e2 +size 63542816 diff --git a/openchatgpt-neox-125m.i1-IQ3_M.gguf b/openchatgpt-neox-125m.i1-IQ3_M.gguf new file mode 100644 index 0000000..2977375 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9265e4c77ec5762ed112494ccdfdca5d0255681c35594e6ab6818bb44c5dd325 +size 91098592 diff --git a/openchatgpt-neox-125m.i1-IQ3_S.gguf b/openchatgpt-neox-125m.i1-IQ3_S.gguf new file mode 100644 index 0000000..ebb38d0 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4ba17e4db7d6c7d575f83d3a8ce736fa9a61041a125755b7f7c67cbd4525aa +size 87025120 diff --git a/openchatgpt-neox-125m.i1-IQ3_XS.gguf b/openchatgpt-neox-125m.i1-IQ3_XS.gguf new file mode 100644 index 0000000..86629e5 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b0710d4c81918e269ba08a4697d683ec33ad0728098c0c64d74aa61cd72ba8f +size 86029792 diff --git a/openchatgpt-neox-125m.i1-IQ3_XXS.gguf b/openchatgpt-neox-125m.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a1b6a98 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:478c23409094dbafddef9bc0db47049ceb6e62e3b659f8998020f731df71bfeb +size 78247200 diff --git a/openchatgpt-neox-125m.i1-IQ4_NL.gguf b/openchatgpt-neox-125m.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3e22eb7 --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d434fbfccfbb5bca478abaabc7c562ecc071ec09805b6369b9941f9bfbbd51f +size 103433856 diff --git a/openchatgpt-neox-125m.i1-IQ4_XS.gguf b/openchatgpt-neox-125m.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6ee786f --- /dev/null +++ b/openchatgpt-neox-125m.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c1606a2d7c7970826e593f2d98a320fb2775d8b218c6aa6a61223b61bdeedf +size 99572992 diff --git a/openchatgpt-neox-125m.i1-Q2_K.gguf b/openchatgpt-neox-125m.i1-Q2_K.gguf new file mode 100644 index 0000000..2609cae --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdb700c8772aa3d82cb548ec75c11b5be62a29d305c6dfd35da99c5c510d181 +size 78071520 diff --git a/openchatgpt-neox-125m.i1-Q2_K_S.gguf b/openchatgpt-neox-125m.i1-Q2_K_S.gguf new file mode 100644 index 0000000..798f197 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0b746f52e11806a8e964364073b49ccf178b3e2fe9d671d52b472e47d1a56f +size 75030240 diff --git a/openchatgpt-neox-125m.i1-Q3_K_L.gguf b/openchatgpt-neox-125m.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9cccb58 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a55ca83ad1bfb36cb2060976e40b3907cef4e65c7a904b73071589dd270004 +size 98969056 diff --git a/openchatgpt-neox-125m.i1-Q3_K_M.gguf b/openchatgpt-neox-125m.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ac1399f --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682380b5ff05d26a1280e57d5ad3aab58a9b9b12bcdc5608a09c7374d0d3faab +size 94545376 diff --git a/openchatgpt-neox-125m.i1-Q3_K_S.gguf b/openchatgpt-neox-125m.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3446f5b --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9e3f7fe174150b5b3f88de7a134f5782e10f1130988be07ca8b5f0f655190f +size 87025120 diff --git a/openchatgpt-neox-125m.i1-Q4_0.gguf b/openchatgpt-neox-125m.i1-Q4_0.gguf new file mode 100644 index 0000000..df95505 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8533e57d13c623ee0eaecc41f5bf69aa400409e948f1d371fcd9041d33a69800 +size 103581312 diff --git a/openchatgpt-neox-125m.i1-Q4_1.gguf b/openchatgpt-neox-125m.i1-Q4_1.gguf new file mode 100644 index 0000000..dfd12f8 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda54a3d91d0e9873010ae0dc4bd5891d0806bb1f12c4f06a3f51ca3d83c5891 +size 111155616 diff --git a/openchatgpt-neox-125m.i1-Q4_K_M.gguf b/openchatgpt-neox-125m.i1-Q4_K_M.gguf new file mode 100644 index 0000000..db92fa9 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb691690316a411d6992c328f57c826f78478ebc65fe7b7f8acea013852510d4 +size 109737600 diff --git a/openchatgpt-neox-125m.i1-Q4_K_S.gguf b/openchatgpt-neox-125m.i1-Q4_K_S.gguf new file mode 100644 index 0000000..cafd276 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2503f2e0d673b42041a1506742532b80bad0a26aa35decde9fee96bd973dcd +size 103728768 diff --git a/openchatgpt-neox-125m.i1-Q5_K_M.gguf b/openchatgpt-neox-125m.i1-Q5_K_M.gguf new file mode 100644 index 0000000..56d5f27 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89272741487a9771e189e88e4281248fd4a3b34aa8b0c8698142b99b7c6b776f +size 123577536 diff --git a/openchatgpt-neox-125m.i1-Q5_K_S.gguf b/openchatgpt-neox-125m.i1-Q5_K_S.gguf new file mode 100644 index 0000000..19ae825 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04dc9cda981b4ca4a5bd0b22aeac097eb4e209dfa2ad09982279fbdc9bbcd1d +size 118877376 diff --git a/openchatgpt-neox-125m.i1-Q6_K.gguf b/openchatgpt-neox-125m.i1-Q6_K.gguf new file mode 100644 index 0000000..cb376e5 --- /dev/null +++ b/openchatgpt-neox-125m.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4f126c14ac5058f4496877a62dc0d354e10818fee7163a132d2394d2013e24 +size 135286144