From 3c3e87e761bf4afce209d30584bc9513d2449f65 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 29 Sep 2026 10:26:20 +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-7b-open-instruct-i1-GGUF Source: Original Platform --- .gitattributes | 58 ++++++++++++++++ README.md | 76 +++++++++++++++++++++ imatrix.dat | 3 + open-llama-7b-open-instruct.i1-IQ1_M.gguf | 3 + open-llama-7b-open-instruct.i1-IQ1_S.gguf | 3 + open-llama-7b-open-instruct.i1-IQ2_M.gguf | 3 + open-llama-7b-open-instruct.i1-IQ2_S.gguf | 3 + open-llama-7b-open-instruct.i1-IQ2_XS.gguf | 3 + open-llama-7b-open-instruct.i1-IQ2_XXS.gguf | 3 + open-llama-7b-open-instruct.i1-IQ3_M.gguf | 3 + open-llama-7b-open-instruct.i1-IQ3_S.gguf | 3 + open-llama-7b-open-instruct.i1-IQ3_XS.gguf | 3 + open-llama-7b-open-instruct.i1-IQ3_XXS.gguf | 3 + open-llama-7b-open-instruct.i1-IQ4_XS.gguf | 3 + open-llama-7b-open-instruct.i1-Q2_K.gguf | 3 + open-llama-7b-open-instruct.i1-Q2_K_S.gguf | 3 + open-llama-7b-open-instruct.i1-Q3_K_L.gguf | 3 + open-llama-7b-open-instruct.i1-Q3_K_M.gguf | 3 + open-llama-7b-open-instruct.i1-Q3_K_S.gguf | 3 + open-llama-7b-open-instruct.i1-Q4_0.gguf | 3 + open-llama-7b-open-instruct.i1-Q4_K_M.gguf | 3 + open-llama-7b-open-instruct.i1-Q4_K_S.gguf | 3 + open-llama-7b-open-instruct.i1-Q5_K_M.gguf | 3 + open-llama-7b-open-instruct.i1-Q5_K_S.gguf | 3 + open-llama-7b-open-instruct.i1-Q6_K.gguf | 3 + 25 files changed, 203 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 open-llama-7b-open-instruct.i1-IQ1_M.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ1_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ2_M.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ2_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ2_XS.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ2_XXS.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ3_M.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ3_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ3_XS.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ3_XXS.gguf create mode 100644 open-llama-7b-open-instruct.i1-IQ4_XS.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q2_K.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q2_K_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q3_K_L.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q3_K_M.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q3_K_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q4_0.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q4_K_M.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q4_K_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q5_K_M.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q5_K_S.gguf create mode 100644 open-llama-7b-open-instruct.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..27cfcf6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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-7b-open-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-7b-open-instruct.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..a70eb7e --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: VMware/open-llama-7b-open-instruct +datasets: +- VMware/open-instruct-v1-oasst-dolly-hhrlhf +language: +- en +library_name: transformers +license: cc-by-sa-3.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/VMware/open-llama-7b-open-instruct + + +static quants are available at https://huggingface.co/mradermacher/open-llama-7b-open-instruct-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-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-7b-open-instruct-i1-GGUF/resolve/main/open-llama-7b-open-instruct.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..1687d58 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bba1656500e1d1a76bd545f9c81c72e0c793281c17e3d1809bba3440d722c5 +size 4562173 diff --git a/open-llama-7b-open-instruct.i1-IQ1_M.gguf b/open-llama-7b-open-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..22ac0c5 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c93dd5f3972661753076b1d5870bb1fc1d12b250ab3f35724371dee5f918ff +size 1651006336 diff --git a/open-llama-7b-open-instruct.i1-IQ1_S.gguf b/open-llama-7b-open-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..950b6a0 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566ce06e1bc237afca4e94cb4be18361c02d201803674c3cdb6ed51dc3255c8c +size 1528617856 diff --git a/open-llama-7b-open-instruct.i1-IQ2_M.gguf b/open-llama-7b-open-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..14ca988 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0566dcb6bd9eea9ee7f66e31ca95c8346fde98399acf9d3a43211c756747f6 +size 2359786368 diff --git a/open-llama-7b-open-instruct.i1-IQ2_S.gguf b/open-llama-7b-open-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..8c85958 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b83c0c6f9f1b7bcf041c1513786705847470088eefd97943157619d25b5be23f +size 2196601728 diff --git a/open-llama-7b-open-instruct.i1-IQ2_XS.gguf b/open-llama-7b-open-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..227f29d --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1919a65c3631992dad1b822207f4cd226921ac40857f11f4f880410ffc3dfc79 +size 2034948992 diff --git a/open-llama-7b-open-instruct.i1-IQ2_XXS.gguf b/open-llama-7b-open-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..134eb55 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ec9de703f31b305c2835898fe7bc8ef7ebc2f877951b48eaff811c67688c8a +size 1854987136 diff --git a/open-llama-7b-open-instruct.i1-IQ3_M.gguf b/open-llama-7b-open-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..cdedf48 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab95b0b672681c2535ebae2d792c743348d2dfd52d428446141af0f2a5088f0 +size 3114900352 diff --git a/open-llama-7b-open-instruct.i1-IQ3_S.gguf b/open-llama-7b-open-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..43267be --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12a5f6b90d7aa92a922b35d44ce02b7b261fcfc2e9fbddc58f5e5828b2fe23c +size 2948340608 diff --git a/open-llama-7b-open-instruct.i1-IQ3_XS.gguf b/open-llama-7b-open-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f2279b3 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c83cf79f99f071e84923e62a44abbf79504c4f666ff2ca948bc32058b26bbd +size 2796559232 diff --git a/open-llama-7b-open-instruct.i1-IQ3_XXS.gguf b/open-llama-7b-open-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ac8602a --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97f68d291bdbcc59dbf0e49173e5812afbfbbc49e4233614c8b426672c01514 +size 2585426816 diff --git a/open-llama-7b-open-instruct.i1-IQ4_XS.gguf b/open-llama-7b-open-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2f9c5c8 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6b4b1f34b363f3ce070079995f3555e470c60b48f09b30a6c70e662cbd7f64 +size 3619371904 diff --git a/open-llama-7b-open-instruct.i1-Q2_K.gguf b/open-llama-7b-open-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..a307df8 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f9ecc0fdad9725c7cb11f8d196acd66d4860723dfacfb0d85a35671e2e9e75 +size 2532899712 diff --git a/open-llama-7b-open-instruct.i1-Q2_K_S.gguf b/open-llama-7b-open-instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..00df2e6 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19917f2147369203b48ce454817a8167d175e690e1ab47e75b149196a0da676 +size 2319580032 diff --git a/open-llama-7b-open-instruct.i1-Q3_K_L.gguf b/open-llama-7b-open-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..57fc052 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2354e1b47faa3ec76485fed5b268abdbbebdaa1d0323d5a6e34efc3744a78d0 +size 3597147008 diff --git a/open-llama-7b-open-instruct.i1-Q3_K_M.gguf b/open-llama-7b-open-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..bb214d3 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a211d5d1693be96fdb95405dba0ff8bf086cfaa229cc489614457400e10602 +size 3298040704 diff --git a/open-llama-7b-open-instruct.i1-Q3_K_S.gguf b/open-llama-7b-open-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..fcf3ad7 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54fe67ee3d212aa95f6116252986a5d8079518eaf1e28b3f9c9ba96920252f92 +size 2948340608 diff --git a/open-llama-7b-open-instruct.i1-Q4_0.gguf b/open-llama-7b-open-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..16b4f41 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ba244dd2623f812500ae398f57fe6d84de39db13811f4bf1def639ccbdc792 +size 3837115264 diff --git a/open-llama-7b-open-instruct.i1-Q4_K_M.gguf b/open-llama-7b-open-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..64062f9 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbc75715882e966bf0ffe4d21a6bac951f508276d44fb5e06045238daca60f0 +size 4081040256 diff --git a/open-llama-7b-open-instruct.i1-Q4_K_S.gguf b/open-llama-7b-open-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bba4a1e --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ee86647f6b3bf287b25d5564148ce49d03336530ac3a544f1c5219a2ee0d24 +size 3856776064 diff --git a/open-llama-7b-open-instruct.i1-Q5_K_M.gguf b/open-llama-7b-open-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..704e979 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c210ecc2d4938054408c0836893ff1f8824b96e593f7c6366ce59a14c998666e +size 4783192960 diff --git a/open-llama-7b-open-instruct.i1-Q5_K_S.gguf b/open-llama-7b-open-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b136907 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d358fe753a424b3c9943dcb5a7ad7ea8e50278bc3ba0525f7e8f06db3ac9b00 +size 4651727744 diff --git a/open-llama-7b-open-instruct.i1-Q6_K.gguf b/open-llama-7b-open-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..bdc3aa4 --- /dev/null +++ b/open-llama-7b-open-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d84aefb8b692c9835f30b08e448bef00f4cceb0667820a6f721c3636735a38e +size 5529230208