From 818136b160fc3be5883b38240ac017b0d0dde83a Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 10 Aug 2026 19:27:24 +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/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++ README.md | 78 +++++++++++++++++++ imatrix.dat | 3 + ...a-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf | 3 + ...a-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf | 3 + ...a-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf | 3 + ...a-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf | 3 + ...0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf | 3 + ...a-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf | 3 + ...a-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf | 3 + ...0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf | 3 + ...ma-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf | 3 + ...ma-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf | 3 + ...ma-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf | 3 + ...-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf | 3 + ...ma-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf | 3 + 27 files changed, 213 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf create mode 100644 open-llama-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ff3b3e5 --- /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 +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a748b2d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: VMware/open-llama-0.7T-7B-open-instruct-v1.1 +datasets: +- VMware/open-instruct-v1.1-oasst-dolly-hhrlhf +language: +- en +library_name: transformers +license: cc +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/VMware/open-llama-0.7T-7B-open-instruct-v1.1 + + +static quants are available at https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-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/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf) | i1-Q4_1 | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-0.7T-7B-open-instruct-v1.1-i1-GGUF/resolve/main/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | 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..d402632 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7074500a773ee7264a4bc328ddc3dd64f4b72132507e057fa3e2d31c295b42 +size 4562173 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..6a15df0 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16197e98633a4e2c263c8edf39491029652bc25b3a267f30a342a6392a7f7a6 +size 1651006432 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..72b574d --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f26aaa48c2ea5fc4ff365ed51f086c9b4e6e3d9b0d6e8636edd4fc6c7d8b9bb +size 1528617952 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..8b0960f --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c0df3101816a5b0fe490e752cd8d5fa602c715f8ef8d89dc7052a2056784b5 +size 2359786464 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..aa807a7 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b28552490ae3176c124e61f2f7efa365eed18bdfbd71306521e7b1e2edd54f1 +size 2196601824 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c6e6f8f --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843a33e10153cbd2d82dbdc1efa8e134f1f57e369b24f93bad8210f4ffdcb593 +size 2034949088 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..adeb97a --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60f596cc2acf9ad1bc3281534eba8f3f9860f32774ae06de97f250fd36aba4d +size 1854987232 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..65c6a01 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5065c690b0f3490ff6ce4201e6a841a7c83872bb41ff7c4f3e8c29601f9f5791 +size 3114900448 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..a673b62 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f014bfe045179f7133cc7c13f64b7f00e2abf2d5a1e1e10e4362d06fcb71b3c +size 2948340704 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c96fd7f --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ec2f7ab85c6ac483bf748a774cc2e0d297897d329df5502a1e4fcb2021b8c9 +size 2796559328 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3d9512b --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec0fd498d83193daf1e9ac363346db3d466961e0a8f6851c8bb242f6551883a +size 2585426912 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..db3db23 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae96b43762bc804e191e6cb4a372f6b616a5f91f86467ee1cfc8685288f3ce8b +size 3825843168 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..11e984c --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75acfeec979e801864c0a536b3f7ed8fb0de680491537185172b37cdfc80d220 +size 3619372000 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf new file mode 100644 index 0000000..edfce12 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d1b6726951103affbdeaa70fd49c0ea40fd7e40cee92fdecdcf30ea8863e8f0 +size 2532899808 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..93978d3 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876a94bfa3ed1eaf3eaad32a736aa87631d1bd69718e1894812402f509d848fd +size 2319580128 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f0b5dd0 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b9d534f200391cfa1c2933cf5803370b77c4307ad3e26aca99b9b6b81129fe +size 3597147104 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a589beb --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:628b947bc7e679f4f63f249c465084223eb7262bf7c8e13e4b22ecb29c14f49b +size 3298040800 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4f4f450 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9acc50c94cd6103d328d2a60cc8d581182e1becdfb5664da2f720a4112f1a6 +size 2948340704 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf new file mode 100644 index 0000000..8f0af78 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28da8f1cf246a688fd4745c03896fd8c691ef7d4c191d943bfee943dbc4d40b +size 3837115360 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf new file mode 100644 index 0000000..850d887 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399217f7a9ce3cef995a1fcbb45df10f7e6a979483e0daa49413868faa61f679 +size 4238785504 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..46a1ae8 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717e746530db22e99fd68099fc4b0926aaee2b340476678959919686ffb04f38 +size 4081040352 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..312200c --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b556bf4e9a4289e400d0cdc56e13b30ac7812f2c8bf59301d5a0809de0035f1 +size 3856776160 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..031e0b7 --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfef0315f0c456f9e519e38e8c4bfbdfb9ad0f07ba298656b2f6e731e0b573dd +size 4783193056 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..582d73e --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca89230a21755f0089237155245b021547e46b40f69296ba4e2754142a3dae3 +size 4651727840 diff --git a/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf new file mode 100644 index 0000000..a2ddfdc --- /dev/null +++ b/open-llama-0.7T-7B-open-instruct-v1.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1767d111f73f12ce8afae68f32c749485b70f67a03b04e1276876b659a356ec7 +size 5529230304