From 3d2481d2b31ea71cbbc3d69640d23df53c5df769 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 5 Aug 2026 11:19:16 +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/llama-3.1-8b-instruct-ortho-v3-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ README.md | 76 +++++++++++++++++++ imatrix.dat | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf | 3 + ...a-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ3_S.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf | 3 + ...a-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf | 3 + ...-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf | 3 + ...-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf | 3 + ...-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf | 3 + llama-3.1-8b-instruct-ortho-v3.i1-Q6_K.gguf | 3 + 27 files changed, 211 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ3_S.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf create mode 100644 llama-3.1-8b-instruct-ortho-v3.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b5215d1 --- /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 +llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.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..e6514ed --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3 +language: +- en +library_name: transformers +license: wtfpl +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3 + + +static quants are available at https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-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/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-i1-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.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..43a0373 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee3b2418cbea9a37893be2a493a81669c565f88a602c479406ec6ae9013fe20 +size 4988157 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf new file mode 100644 index 0000000..9b01b61 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a60df85a124f4329cbe020c902fa27505f576062cabf198b592f2c778a5dada +size 2161972800 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf new file mode 100644 index 0000000..2b7aa74 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008cab50b9bacc7472f52aede3ee4dfff2472f07c5e2785d6c60de572d7a9e0a +size 2019628608 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf new file mode 100644 index 0000000..952c21b --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9896bc08828487f843b6eb0ddffa16d10153589bec89e61ca48fd8cb83982216 +size 2948281920 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf new file mode 100644 index 0000000..9363473 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:507387d393671c8147bac07910fbe3c57d63c129804d3a184fda896a3bf6920b +size 2758489664 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..038f0cc --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c68c04ec5d619c32c1993a797e86acf24f96405cd24b7e0e49f315ff7a5ee7 +size 2605782592 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9966d4c --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186b7ec33fef4d92c0c4a21dd256be10bddcf29e88f20faec5e83d922992b02f +size 2399213120 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf new file mode 100644 index 0000000..aaa0d90 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15c0de4e57cbe7b08f2218c768a23d16469f3802d7f5db14ee3ee563fc952a2 +size 3784824384 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_S.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_S.gguf new file mode 100644 index 0000000..3ad0621 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31afd8ce1be481d824a941e6e6070c10e70a08728e9e71afd84fc618ba8a6aa1 +size 3682326080 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..67845f3 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688f6f8241d7abff179f2fbeed1bb1ab4decb5e3b40749d00c3a440c1bd31980 +size 3518748224 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cc74fd1 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087d337d2878f13f257ecd6c65f237eb3dd75e902be5ef2ab97aa862686d08c1 +size 3274913344 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..bf98eba --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdcb2e27be865bb84c6fda58a6fc96de9cecab8e3a7ac71d2deded2e831a3e9 +size 4447663680 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf new file mode 100644 index 0000000..43601b1 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e5d7e1d39232bbf2cfe13afdf6507637ce2728a889ca79b1784fc79e49038d +size 3179132480 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..33f1cf5 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab02d0afafae6794ee0942a0ebf777491744a9b71ed8d8533bfdbc53ed968c11 +size 4321957440 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..90d28fe --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ef5c036d7396461252f578ec59f0b6c87825d197d11e743aa2f8ef0daec5e6 +size 4018918976 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ec2b64a --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a05908c5a4735ffda076772cbf1f38a0da7348d335ba9e22437382158a477800 +size 3664500288 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf new file mode 100644 index 0000000..ecbf4d5 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d6546f3c0f7a7271402720455c647b4c108ea4bbdfcc736d6f2715b7887acd +size 4675892800 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..10c0431 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947dd484c4e9b3b63f21567dc9247667e0b5f7017ed6d8c61e447e508b087e6d +size 4661212736 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..17c9817 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9767549ef8782b5c630dcfd8fb4c7c05bc5cb78aa2b1ca7b0ef14050e089bb6e +size 4661212736 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..39fcadc --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4a8e2f3e29d8dd3a9fb46f6402be0c3f940db416c4ba7c9d07e5f3fac9fc7c +size 4661212736 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6af8aab --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f2e096848b2c86c0af52605ecb9b3642696cad8936c960d62ef3256468d535 +size 4920735296 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3c4faa2 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea259915c72cc6db768e0a7433884023846baa6dc6fcc03db09e97d64cee72c9 +size 4692670016 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..fe8ccca --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ade2f91bf77f30db1e1074739601e7ac6123830e0ed80b1c456f68298b68833 +size 5732988480 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..034e863 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5830de5644dc98f22e9b86944a3e2a2d19d00e9ce832fe17c85fab9fff8100aa +size 5599295040 diff --git a/llama-3.1-8b-instruct-ortho-v3.i1-Q6_K.gguf b/llama-3.1-8b-instruct-ortho-v3.i1-Q6_K.gguf new file mode 100644 index 0000000..0f7f9fe --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a53ada96a80905d06e780c00ead434f0e28c153887c8277df66f4a3afc8bf0 +size 6596007488