From 6a2ff3f1808969b9f20b74a848f1b7c56849bae3 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 18 Jun 2026 09:32:17 +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/llama3.1-airoboros3.2-QDT-8B-i1-GGUF Source: Original Platform --- .gitattributes | 57 +++++++++++++++ README.md | 75 ++++++++++++++++++++ imatrix.dat | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ3_S.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf | 3 + llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf | 3 + 24 files changed, 198 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ3_S.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf create mode 100644 llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..835ec92 --- /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 +llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.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..f7c7822 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: nbeerbower/llama3.1-airoboros3.2-QDT-8B +datasets: +- jondurbin/airoboros-3.2 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nbeerbower/llama3.1-airoboros3.2-QDT-8B + + +static quants are available at https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-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/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..6532477 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cf9684c1050eea427ff78dea8aa3ea1befbe52b030965ee714955a716a3cfb +size 4988157 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..c02532a --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5720faaee6efa54c159091aff5eb347b7349a2e492febeb9d82c5dfa1f75a6 +size 2161977376 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..4197ab7 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a51dbcd93a3c67c0f575d3b2f268ba6fe326d498ba5a315eede31ff77960c6 +size 2019633184 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..1aeac7d --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:674d6f7535772d75b08e5af981546c493a9519ff640b97232234c2bf9db57613 +size 2948286496 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..35726a6 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a28a6c5e95268495a09d7940c5d87b47bc03d9bff626718c16cf976e02255a4 +size 2758494240 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c38be82 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fce03e39fad9940c303a36446e1bae048522d6bfbd46f03887d43d79e02452 +size 2605787168 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ccfdf20 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeedc0aec1836a0a74394a3af86a9a8bcba852e05d719fde553703f803371fd9 +size 2399217696 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..6d58469 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f8b61b284a9a7c66005c900ae052f6411d05734bea067c03d96d6ad1663f93 +size 3784828960 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_S.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..3f5d616 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f315a1d128ac5b4ae993e04621a2a0d60d3083c351bc39308393bc522d3800 +size 3682330656 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..38068b1 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58854485cfc8a64ddbfa940c7fa6b69217d699802d7820ca6d9e8ceda97dc1c3 +size 3518752800 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c95437e --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba5e3f913c95c3df7e147818045460decb16b613f477a607e6124debe24e188 +size 3274917920 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0633396 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88dc64bb1f9d3ab3cc5b4b5d22e9a4e2dc1b3df809d4f15a4602e5cd8702b18f +size 4447668256 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..4c96bbe --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879288917b405281e43295adc514f3595f3a70a05326b48d3aac17044a481b32 +size 3179137056 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..223e961 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5274f2e01b8d444fc1a2cb53e61e5e3f4655d178211a9ec0324a5254f584776d +size 4321962016 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3712df7 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649f1114f260ebd2a9ca06ce913521babef658375eb4c5a83471e3174ddeacd8 +size 4018923552 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e98adc0 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c39a1d680136c5ba0d8c9a8e4d0243b75a548e2b96a4e6ac7b11e264180eb6 +size 3664504864 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..8bb5b38 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d981789e0758b3ad986297061f1977a51697d3b4f54d4a54dfc1596641e15e3 +size 4675897376 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f17d958 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1de9d5857b812bd5372325e0ffb70d113e16e8830b4272022883684e88324d3 +size 4920739872 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d7e6291 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5998ea7c09abb2af5d147fcb83b3b7ac63c4104800ad791f75f42decd07764 +size 4692674592 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..50a0e07 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88dfe35071ddb40277bfbb90c9c656b19ac4caeb1e74a8bd29e8fbd0975e9ebd +size 5732993056 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1819ab2 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1848aa8af67974bea4a8faba103e6a9fa85902a4fa25cd2ba42e066d9ee93168 +size 5599299616 diff --git a/llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf b/llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..9c397fc --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f02aaa350e4dcb89d8019c2f99c57c65f9a7bdc226d19d529bc3980feb5154 +size 6596012064