From 3d93e6b0000df8f0566c0aafa9b5bf68289d5699 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 11 Apr 2026 22:41:00 +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/micro-g3.3-8b-instruct-1b-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++++ README.md | 85 +++++++++++++++++++++++ micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf | 3 + micro-g3.3-8b-instruct-1b.i1-Q6_K.gguf | 3 + micro-g3.3-8b-instruct-1b.imatrix.gguf | 3 + 27 files changed, 220 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf create mode 100644 micro-g3.3-8b-instruct-1b.i1-Q6_K.gguf create mode 100644 micro-g3.3-8b-instruct-1b.imatrix.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bfc30b7 --- /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 +micro-g3.3-8b-instruct-1b.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +micro-g3.3-8b-instruct-1b.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..eba494a --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: ibm-ai-platform/micro-g3.3-8b-instruct-1b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ibm-ai-platform/micro-g3.3-8b-instruct-1b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#micro-g3.3-8b-instruct-1b-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-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/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf) | i1-IQ2_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf) | i1-Q2_K | 0.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf) | i1-IQ3_S | 0.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf) | i1-IQ3_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf) | i1-Q4_0 | 0.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf) | i1-Q4_1 | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/micro-g3.3-8b-instruct-1b-i1-GGUF/resolve/main/micro-g3.3-8b-instruct-1b.i1-Q6_K.gguf) | i1-Q6_K | 0.9 | 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/micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf new file mode 100644 index 0000000..00caeea --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c741e8a95055446356e94ac8bf81fc62546bef78995cccc62638c84bda82aad4 +size 343379488 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf new file mode 100644 index 0000000..79cc8b6 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5faf53a964a3de1b0aac06a0f2e826787aa72252bb1904f3bce91cc3d2e602d +size 330845728 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf new file mode 100644 index 0000000..25bd1a5 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:702805cfee8b58bd9af22676cecaa4bde59ff5a4910603088baefcc9459a673f +size 426793344 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf new file mode 100644 index 0000000..403c8f4 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97402393b38b6fcbd82e7c036e0d953402947f4e46e7405e7e4e7191024a9b00 +size 410081664 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3c47abe --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae9f68e62b7aae6501c29d4a76963c51164e23a9c3f935d2b68abbb926682ef +size 382553632 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5020db2 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb2bdd0370f7505a33bac64e4fe88a68700f7cf0f09e8ffecf895a136f7a2c3 +size 364269088 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf new file mode 100644 index 0000000..ce8ab69 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb12b8ab01a87324430f018b1db9d53b9fce3a37939f8fb5a1cd3dc4f8ab752b +size 518711392 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf new file mode 100644 index 0000000..5a5539f --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7653fa67b91b07e02b4bd42bd5f17c6d0007ce6768f4ad74866b0fe9c864efb +size 512026720 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f21f631 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18844b47b6f414caf671defa2aa39a7a7b7485b18cc62b9a1864618e64a92d23 +size 499247200 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1d64992 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b8235f959b173aae9f0f597b8d22f01d48303b3f002ae4fdb000d79dd32e39 +size 456284544 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf new file mode 100644 index 0000000..96e45df --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c277c15b68ca830f68d6933339f9720e3772834d3270cf8d61869ac0e2db9cb +size 618051392 diff --git a/micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf b/micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7a238a5 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3cb7921a76f8b9ff9f9f505b8e27fd984486323085edf41c6b60e9dc28cb0fc +size 593474496 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf b/micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf new file mode 100644 index 0000000..fffc3c7 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83adba2af19be88fb524630d74267052e1250d410185686301450b26d9dc3042 +size 453238016 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf b/micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d1823c8 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c3953d2f75409a865dadbdecff44e86ea350f1feda15dfcd8e0b98b05d8b6b +size 432151808 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf b/micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..68da9ee --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efafa183a1c241d835ab73834362b74c9a9cfa2a09d1b80c7ba0b08751c39107 +size 567126112 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf b/micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2c0a4f1 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0873b54266bc574bd679e91795a618d956f89ed8c49c6f6916966fd661885c +size 540649568 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf b/micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..90f1e0d --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6947a78cbc137e8121764d6c83aa6be636b21237322e7d4688aaefde51253678 +size 510355552 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf b/micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf new file mode 100644 index 0000000..44cc598 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6f05757466a9f5df0e94bbab4c75aa201cb0ca890781a194a4c61202d10fa2 +size 616478528 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf b/micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf new file mode 100644 index 0000000..366eea8 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803fda94f5b946df325d414879eda5b1cd13c0830be9a94973efc3614c915900 +size 666418752 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf b/micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b1ee2e4 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf9ca0412587bdfbca9e9aebb060fa6b37735910ab27e5b44bdb00808e9fa9d +size 631076672 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf b/micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a7ce8b1 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a08c0a270ac0ff85e1dabbc87e00ff91e614006f159916f9ac666cc2680001 +size 618051392 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf b/micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..81909bc --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f554a9b7a2a16048f5992a1bcc53a1b7ea05e6101d852d8db6fc67e07f52697c +size 723879232 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf b/micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..086b63b --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182c28744d1946b616195659ab3d57044d34a6c757ea7ce7f9de3960b373475c +size 716358976 diff --git a/micro-g3.3-8b-instruct-1b.i1-Q6_K.gguf b/micro-g3.3-8b-instruct-1b.i1-Q6_K.gguf new file mode 100644 index 0000000..248d0ae --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6c9341aa4b3d794e5e1966e5796dde237a82b75d1ff061220497bfed3d4ca7 +size 822481952 diff --git a/micro-g3.3-8b-instruct-1b.imatrix.gguf b/micro-g3.3-8b-instruct-1b.imatrix.gguf new file mode 100644 index 0000000..1c3c623 --- /dev/null +++ b/micro-g3.3-8b-instruct-1b.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d91ad6c6f3c76ae423cfde5d389a6b2b102577b4168f757be548a24fe20f7c90 +size 451904