From 33821bc9a67bc08364f75f90935c4a057e4100b1 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 20 Jun 2026 11:04:16 +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/open-llama-13b-open-instruct-i1-GGUF Source: Original Platform --- .gitattributes | 58 +++++++++++++++ README.md | 76 ++++++++++++++++++++ imatrix.dat | 3 + open-llama-13b-open-instruct.i1-IQ1_M.gguf | 3 + open-llama-13b-open-instruct.i1-IQ1_S.gguf | 3 + open-llama-13b-open-instruct.i1-IQ2_M.gguf | 3 + open-llama-13b-open-instruct.i1-IQ2_S.gguf | 3 + open-llama-13b-open-instruct.i1-IQ2_XS.gguf | 3 + open-llama-13b-open-instruct.i1-IQ2_XXS.gguf | 3 + open-llama-13b-open-instruct.i1-IQ3_M.gguf | 3 + open-llama-13b-open-instruct.i1-IQ3_S.gguf | 3 + open-llama-13b-open-instruct.i1-IQ3_XS.gguf | 3 + open-llama-13b-open-instruct.i1-IQ3_XXS.gguf | 3 + open-llama-13b-open-instruct.i1-IQ4_XS.gguf | 3 + open-llama-13b-open-instruct.i1-Q2_K.gguf | 3 + open-llama-13b-open-instruct.i1-Q2_K_S.gguf | 3 + open-llama-13b-open-instruct.i1-Q3_K_L.gguf | 3 + open-llama-13b-open-instruct.i1-Q3_K_M.gguf | 3 + open-llama-13b-open-instruct.i1-Q3_K_S.gguf | 3 + open-llama-13b-open-instruct.i1-Q4_0.gguf | 3 + open-llama-13b-open-instruct.i1-Q4_K_M.gguf | 3 + open-llama-13b-open-instruct.i1-Q4_K_S.gguf | 3 + open-llama-13b-open-instruct.i1-Q5_K_M.gguf | 3 + open-llama-13b-open-instruct.i1-Q5_K_S.gguf | 3 + open-llama-13b-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-13b-open-instruct.i1-IQ1_M.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ1_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ2_M.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ2_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ2_XS.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ2_XXS.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ3_M.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ3_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ3_XS.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ3_XXS.gguf create mode 100644 open-llama-13b-open-instruct.i1-IQ4_XS.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q2_K.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q2_K_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q3_K_L.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q3_K_M.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q3_K_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q4_0.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q4_K_M.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q4_K_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q5_K_M.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q5_K_S.gguf create mode 100644 open-llama-13b-open-instruct.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fb41bd7 --- /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-13b-open-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-open-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +open-llama-13b-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..9d0d1a7 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: VMware/open-llama-13b-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-13b-open-instruct + + +static quants are available at https://huggingface.co/mradermacher/open-llama-13b-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-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | | +| [GGUF](https://huggingface.co/mradermacher/open-llama-13b-open-instruct-i1-GGUF/resolve/main/open-llama-13b-open-instruct.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | 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..21583a8 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76746da4df8f072854b85bed9d7abafcb2da42a16dd1402f8238f5a391380744 +size 7136325 diff --git a/open-llama-13b-open-instruct.i1-IQ1_M.gguf b/open-llama-13b-open-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..6463555 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7919cd019a40155c02960b5660d547a5b55fbab3503d178de24600b22dfcb3 +size 3138645056 diff --git a/open-llama-13b-open-instruct.i1-IQ1_S.gguf b/open-llama-13b-open-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..cf0535a --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9befe3dd63caa313dd030d48cf2751d2431f53883558b027325a3825db5b499 +size 2898721856 diff --git a/open-llama-13b-open-instruct.i1-IQ2_M.gguf b/open-llama-13b-open-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..89c75b0 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7cd2e6c52d86e9bfe52c6c9c0986d5464109f1855f1d25db5bf950584674807 +size 4517614656 diff --git a/open-llama-13b-open-instruct.i1-IQ2_S.gguf b/open-llama-13b-open-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..3e9d204 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6542588fe62292b78f3bdd25fca207db7671962ee99f9ed84f06b9cb2310f5 +size 4197717056 diff --git a/open-llama-13b-open-instruct.i1-IQ2_XS.gguf b/open-llama-13b-open-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c5c2ebc --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0765ba9fb7cc0d55186f72c5ae9cbc5d8c8621a538f1948dd9422258245b2ac6 +size 3891182656 diff --git a/open-llama-13b-open-instruct.i1-IQ2_XXS.gguf b/open-llama-13b-open-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c02ebd6 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21084cab917106e810f910bb8beed28ec8eb257667e78021af68530d4d1c3c04 +size 3538517056 diff --git a/open-llama-13b-open-instruct.i1-IQ3_M.gguf b/open-llama-13b-open-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..c1c19d7 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1447d8b867beb290bd3408e28951ea02f1ff6dbae17376ae9ff973b63c60392 +size 5984545856 diff --git a/open-llama-13b-open-instruct.i1-IQ3_S.gguf b/open-llama-13b-open-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..2872f24 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f0571c462d9be948c775bc071e8084e531b4e9df6745d1802b3ea5a53cee4e +size 5659016256 diff --git a/open-llama-13b-open-instruct.i1-IQ3_XS.gguf b/open-llama-13b-open-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..200a5f6 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0652680e103d9b056e8750bc4f72de93963cf0af9934dc6663b410e8c9124d34 +size 5361646656 diff --git a/open-llama-13b-open-instruct.i1-IQ3_XXS.gguf b/open-llama-13b-open-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..003db11 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4181d7c2aba4675ec27a0b612a63728bb7da20c4c744cf38ce3af3505fe5c6ce +size 4960597056 diff --git a/open-llama-13b-open-instruct.i1-IQ4_XS.gguf b/open-llama-13b-open-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..33ca6c8 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47cd534550bcc529aa848662d182d52f0c9f9a4a8fdeee0e3c043eb9816388be +size 6964257856 diff --git a/open-llama-13b-open-instruct.i1-Q2_K.gguf b/open-llama-13b-open-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..6873948 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eabe79f3ef4f5c68c35508b089a6c786a11c6e0eeda5535dbfd2cab8f39224e +size 4854305856 diff --git a/open-llama-13b-open-instruct.i1-Q2_K_S.gguf b/open-llama-13b-open-instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..fa47b92 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abb5ec410ed0b45ff72168ee885f6b531d21a804b30c7244c52549ece3de095 +size 4436718656 diff --git a/open-llama-13b-open-instruct.i1-Q3_K_L.gguf b/open-llama-13b-open-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..039840d --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2291ea0005e5473390da4b1744cae2ad037e4b5d5b7c6b1b20041917baac72 +size 6929595456 diff --git a/open-llama-13b-open-instruct.i1-Q3_K_M.gguf b/open-llama-13b-open-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..71afaa2 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894e076b556a5e3496ab56a56604f543af72f78cb953afbbdde2f8012627d36d +size 6337805376 diff --git a/open-llama-13b-open-instruct.i1-Q3_K_S.gguf b/open-llama-13b-open-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..892bc69 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8246bf9fdc92851eab926e6eb23b1afcf33ffef996a09eab46e6711311199250 +size 5659016256 diff --git a/open-llama-13b-open-instruct.i1-Q4_0.gguf b/open-llama-13b-open-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..19909bd --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f3b365db05bdfaafa448860feb683a6a055f902df1dad2f7d69f12f4fc0f93 +size 7387989056 diff --git a/open-llama-13b-open-instruct.i1-Q4_K_M.gguf b/open-llama-13b-open-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3c663ce --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990609fe92272141ef754093fa40b08a2fbd2dbcbc744f7cc88379b68bbf95ad +size 7865992256 diff --git a/open-llama-13b-open-instruct.i1-Q4_K_S.gguf b/open-llama-13b-open-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..98e04ff --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17a618f3b20def04f95c244887f14159c75ebcfff096288e516489c22fe28ee +size 7423214656 diff --git a/open-llama-13b-open-instruct.i1-Q5_K_M.gguf b/open-llama-13b-open-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4e3b7e2 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a102999eae8b4714c3a0a42168e9db56ec43caf39292c002d3e4219bf8924c +size 9229960256 diff --git a/open-llama-13b-open-instruct.i1-Q5_K_S.gguf b/open-llama-13b-open-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ee76749 --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc51ccbe464f1b937517440a4c2d8c6f50009bb51b95f792cd5123ebc44a675 +size 8972321856 diff --git a/open-llama-13b-open-instruct.i1-Q6_K.gguf b/open-llama-13b-open-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..a38597b --- /dev/null +++ b/open-llama-13b-open-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef2c3a25d332d8a56819cd0908eba5ce4ae683fae56c7d5a280ec38073a041b +size 10679176256