From 7ae8d7b33fbfe7d3fd03d54e9a27fa1a5cae149f Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 9 Apr 2026 13:46:24 +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/llama-33B-instructed-i1-GGUF Source: Original Platform --- .gitattributes | 59 ++++++++++++++++++++++ README.md | 75 ++++++++++++++++++++++++++++ imatrix.dat | 3 ++ llama-33B-instructed.i1-IQ1_M.gguf | 3 ++ llama-33B-instructed.i1-IQ1_S.gguf | 3 ++ llama-33B-instructed.i1-IQ2_M.gguf | 3 ++ llama-33B-instructed.i1-IQ2_S.gguf | 3 ++ llama-33B-instructed.i1-IQ2_XS.gguf | 3 ++ llama-33B-instructed.i1-IQ2_XXS.gguf | 3 ++ llama-33B-instructed.i1-IQ3_M.gguf | 3 ++ llama-33B-instructed.i1-IQ3_S.gguf | 3 ++ llama-33B-instructed.i1-IQ3_XS.gguf | 3 ++ llama-33B-instructed.i1-IQ3_XXS.gguf | 3 ++ llama-33B-instructed.i1-IQ4_XS.gguf | 3 ++ llama-33B-instructed.i1-Q2_K.gguf | 3 ++ llama-33B-instructed.i1-Q2_K_S.gguf | 3 ++ llama-33B-instructed.i1-Q3_K_L.gguf | 3 ++ llama-33B-instructed.i1-Q3_K_M.gguf | 3 ++ llama-33B-instructed.i1-Q3_K_S.gguf | 3 ++ llama-33B-instructed.i1-Q4_0.gguf | 3 ++ llama-33B-instructed.i1-Q4_1.gguf | 3 ++ llama-33B-instructed.i1-Q4_K_M.gguf | 3 ++ llama-33B-instructed.i1-Q4_K_S.gguf | 3 ++ llama-33B-instructed.i1-Q5_K_M.gguf | 3 ++ llama-33B-instructed.i1-Q5_K_S.gguf | 3 ++ llama-33B-instructed.i1-Q6_K.gguf | 3 ++ 26 files changed, 206 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 imatrix.dat create mode 100644 llama-33B-instructed.i1-IQ1_M.gguf create mode 100644 llama-33B-instructed.i1-IQ1_S.gguf create mode 100644 llama-33B-instructed.i1-IQ2_M.gguf create mode 100644 llama-33B-instructed.i1-IQ2_S.gguf create mode 100644 llama-33B-instructed.i1-IQ2_XS.gguf create mode 100644 llama-33B-instructed.i1-IQ2_XXS.gguf create mode 100644 llama-33B-instructed.i1-IQ3_M.gguf create mode 100644 llama-33B-instructed.i1-IQ3_S.gguf create mode 100644 llama-33B-instructed.i1-IQ3_XS.gguf create mode 100644 llama-33B-instructed.i1-IQ3_XXS.gguf create mode 100644 llama-33B-instructed.i1-IQ4_XS.gguf create mode 100644 llama-33B-instructed.i1-Q2_K.gguf create mode 100644 llama-33B-instructed.i1-Q2_K_S.gguf create mode 100644 llama-33B-instructed.i1-Q3_K_L.gguf create mode 100644 llama-33B-instructed.i1-Q3_K_M.gguf create mode 100644 llama-33B-instructed.i1-Q3_K_S.gguf create mode 100644 llama-33B-instructed.i1-Q4_0.gguf create mode 100644 llama-33B-instructed.i1-Q4_1.gguf create mode 100644 llama-33B-instructed.i1-Q4_K_M.gguf create mode 100644 llama-33B-instructed.i1-Q4_K_S.gguf create mode 100644 llama-33B-instructed.i1-Q5_K_M.gguf create mode 100644 llama-33B-instructed.i1-Q5_K_S.gguf create mode 100644 llama-33B-instructed.i1-Q6_K.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c5b6ce0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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-33B-instructed.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-33B-instructed.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..ea90be3 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Secbone/llama-33B-instructed +language: +- en +library_name: transformers +license: gpl-3.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Secbone/llama-33B-instructed + + +static quants are available at https://huggingface.co/mradermacher/llama-33B-instructed-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-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ1_S.gguf) | i1-IQ1_S | 7.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ1_M.gguf) | i1-IQ1_M | 7.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q2_K.gguf) | i1-Q2_K | 12.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_S.gguf) | i1-IQ3_S | 14.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_0.gguf) | i1-Q4_0 | 18.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_1.gguf) | i1-Q4_1 | 20.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.1 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | 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..93b71c6 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3053fbe43b3d89ad7943f6f841235fa6d558f2f273f14058a25da993a47544 +size 13899385 diff --git a/llama-33B-instructed.i1-IQ1_M.gguf b/llama-33B-instructed.i1-IQ1_M.gguf new file mode 100644 index 0000000..6ab091c --- /dev/null +++ b/llama-33B-instructed.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e29691e70a04f664ead82e47050b7d10ab9e9e7ff49cc76bc72aa43621d04f +size 7728532960 diff --git a/llama-33B-instructed.i1-IQ1_S.gguf b/llama-33B-instructed.i1-IQ1_S.gguf new file mode 100644 index 0000000..d0b0977 --- /dev/null +++ b/llama-33B-instructed.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95201345d46e4ba38cd13563ecbed09a734c95f4da12b7282ac9b1f688717915 +size 7120307680 diff --git a/llama-33B-instructed.i1-IQ2_M.gguf b/llama-33B-instructed.i1-IQ2_M.gguf new file mode 100644 index 0000000..f86ad28 --- /dev/null +++ b/llama-33B-instructed.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d157319b755fe0832e10e4b2eb1bc867ac8ec80ae07b452cece091eaaa8575 +size 11197440480 diff --git a/llama-33B-instructed.i1-IQ2_S.gguf b/llama-33B-instructed.i1-IQ2_S.gguf new file mode 100644 index 0000000..4fd7898 --- /dev/null +++ b/llama-33B-instructed.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:218cc44986610b0fba4a0407a3404424c0e4741e1515b01a4689fd79dd43b7c3 +size 10386473440 diff --git a/llama-33B-instructed.i1-IQ2_XS.gguf b/llama-33B-instructed.i1-IQ2_XS.gguf new file mode 100644 index 0000000..cbb7709 --- /dev/null +++ b/llama-33B-instructed.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bf160caf05636efd8c049907e10e0b9f14876ba1b1a37d66b2cd1ab97e2247 +size 9636275680 diff --git a/llama-33B-instructed.i1-IQ2_XXS.gguf b/llama-33B-instructed.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d81b39e --- /dev/null +++ b/llama-33B-instructed.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31fb5023008c3b6f4d2ad0ac6f646224b65b4a3f0d8906d6c15f21c58845a97 +size 8742241760 diff --git a/llama-33B-instructed.i1-IQ3_M.gguf b/llama-33B-instructed.i1-IQ3_M.gguf new file mode 100644 index 0000000..6080619 --- /dev/null +++ b/llama-33B-instructed.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af34d7133d459de72816c61f898cdb49ded51fb630a85e5c3f2a5e5a549d8901 +size 14881070560 diff --git a/llama-33B-instructed.i1-IQ3_S.gguf b/llama-33B-instructed.i1-IQ3_S.gguf new file mode 100644 index 0000000..f498886 --- /dev/null +++ b/llama-33B-instructed.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334625006f336c26f901e90b9aa7bfdecd6f31245e3c0637ec5822bfda493a85 +size 14064113120 diff --git a/llama-33B-instructed.i1-IQ3_XS.gguf b/llama-33B-instructed.i1-IQ3_XS.gguf new file mode 100644 index 0000000..07f0408 --- /dev/null +++ b/llama-33B-instructed.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb40c015b3aae5bdc85c3faebb4eaa80502508a408c7ef0e0065355e892b25c8 +size 13311718880 diff --git a/llama-33B-instructed.i1-IQ3_XXS.gguf b/llama-33B-instructed.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0504d34 --- /dev/null +++ b/llama-33B-instructed.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b738ca9fe8da8f0b67c7386037a9d7b3c52f95bd756d608d4ded23eac9a8ac +size 12323369440 diff --git a/llama-33B-instructed.i1-IQ4_XS.gguf b/llama-33B-instructed.i1-IQ4_XS.gguf new file mode 100644 index 0000000..04beb44 --- /dev/null +++ b/llama-33B-instructed.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607fc46f6063fe9c0d54fb2eb515374da871a3954e4e7360bc3e457e08a304f6 +size 17346120160 diff --git a/llama-33B-instructed.i1-Q2_K.gguf b/llama-33B-instructed.i1-Q2_K.gguf new file mode 100644 index 0000000..80a19a3 --- /dev/null +++ b/llama-33B-instructed.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e9fac02a6a351d877c1b36931e55bbc888b4b8981fc27954fe6213945eeb5d +size 12048876000 diff --git a/llama-33B-instructed.i1-Q2_K_S.gguf b/llama-33B-instructed.i1-Q2_K_S.gguf new file mode 100644 index 0000000..1a4922c --- /dev/null +++ b/llama-33B-instructed.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4925f8ac7a3fe1f95a6d2ecc93f9962264bc70054aeeaefa1a5673cc3e00242f +size 10977792480 diff --git a/llama-33B-instructed.i1-Q3_K_L.gguf b/llama-33B-instructed.i1-Q3_K_L.gguf new file mode 100644 index 0000000..adc6391 --- /dev/null +++ b/llama-33B-instructed.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285b13ceaac91ec71ebb0b935b0cfaf92eb5eac4728911d08bd38fd3bed48943 +size 17279759840 diff --git a/llama-33B-instructed.i1-Q3_K_M.gguf b/llama-33B-instructed.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c0ac351 --- /dev/null +++ b/llama-33B-instructed.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f6d06cdbd22e19ae7ba2bf73bf549f0b6a9c8a15425bf28377b99845b2081c +size 15776462304 diff --git a/llama-33B-instructed.i1-Q3_K_S.gguf b/llama-33B-instructed.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6dcb192 --- /dev/null +++ b/llama-33B-instructed.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a150630055a8ce817d397cae7fa82dbe7b2b0347ec6d80edd0373ad8bae0e3c0 +size 14064113120 diff --git a/llama-33B-instructed.i1-Q4_0.gguf b/llama-33B-instructed.i1-Q4_0.gguf new file mode 100644 index 0000000..85c0e5e --- /dev/null +++ b/llama-33B-instructed.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4613ee201da6f495b802c0c1ea70355638bbb6ad0b11ee52ae741f0a69bd3dd2 +size 18408151520 diff --git a/llama-33B-instructed.i1-Q4_1.gguf b/llama-33B-instructed.i1-Q4_1.gguf new file mode 100644 index 0000000..d8115ce --- /dev/null +++ b/llama-33B-instructed.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34de322241f75d0b9dbc9cc7eba8c2c21d1d4815b3081f118292085d336a88f +size 20375665120 diff --git a/llama-33B-instructed.i1-Q4_K_M.gguf b/llama-33B-instructed.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4cfdac0 --- /dev/null +++ b/llama-33B-instructed.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d320df0f3633fd3957be219253d22480754918592177e9cba1a0d4b19347cd +size 19621140960 diff --git a/llama-33B-instructed.i1-Q4_K_S.gguf b/llama-33B-instructed.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6aa1426 --- /dev/null +++ b/llama-33B-instructed.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18e9dbea0230a76cea76449123e4a3bb14b1cddb2e6afab648f82f2c04b1fd5 +size 18482485728 diff --git a/llama-33B-instructed.i1-Q5_K_M.gguf b/llama-33B-instructed.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5ca0138 --- /dev/null +++ b/llama-33B-instructed.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8a8009ab604324ba7286b4677977c08f6df4715021f8b0259f7e7ca9f4a28e +size 23047117280 diff --git a/llama-33B-instructed.i1-Q5_K_S.gguf b/llama-33B-instructed.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3d8a66e --- /dev/null +++ b/llama-33B-instructed.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344489fb5f752ce2f66ee9058ce6a5fc8e543e826fc41e1d8152188284c988c3 +size 22395361760 diff --git a/llama-33B-instructed.i1-Q6_K.gguf b/llama-33B-instructed.i1-Q6_K.gguf new file mode 100644 index 0000000..1f2799c --- /dev/null +++ b/llama-33B-instructed.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a877b6befd2c9bca93e819793350b129932b62892dc3a863bc5790a9c738716 +size 26687217120