From e343f0f2020ce0245f8d59131946a12ca9b8998b Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 21 Jun 2026 05:52:16 +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/llama3.1-8B-toucan-full-sft-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ README.md | 84 +++++++++++++++++++++ llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ3_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf | 3 + llama3.1-8B-toucan-full-sft.i1-Q6_K.gguf | 3 + llama3.1-8B-toucan-full-sft.imatrix.gguf | 3 + 27 files changed, 219 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ3_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf create mode 100644 llama3.1-8B-toucan-full-sft.i1-Q6_K.gguf create mode 100644 llama3.1-8B-toucan-full-sft.imatrix.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..908d84a --- /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 +llama3.1-8B-toucan-full-sft.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-toucan-full-sft.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..27ce896 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: rifoag/llama3.1-8B-toucan-full-sft +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/rifoag/llama3.1-8B-toucan-full-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.1-8B-toucan-full-sft-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-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/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-toucan-full-sft-i1-GGUF/resolve/main/llama3.1-8B-toucan-full-sft.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/llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf new file mode 100644 index 0000000..f4ff86a --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68cb74dd57679cabe1fb4120cb8da47198941016ab2b85e2d271faeeb17bfc4 +size 2161977120 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf new file mode 100644 index 0000000..61872bb --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688369381d500fdd65b0db1ed802a0520abc9ef302c6361f073edc6b4018b869 +size 2019632928 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf new file mode 100644 index 0000000..9c3679e --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c700702aabbae57df6f49096fd3318f0b5472aa90eeb34c3c28bbe1ef7f23ad1 +size 2948286240 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf new file mode 100644 index 0000000..8a903e5 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff32df44f516d1aa852133ac7953e2c07a305df6b609cb856da9bf713f621cbd +size 2758493984 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf new file mode 100644 index 0000000..59fe94f --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8024316a27ec83d83f03d20bf2f4e571cd19b2ec85b944c1cbae38433d92f077 +size 2605786912 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..57e28cb --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a3bc77b8e509b968748a7c48282f3923bffe58b8793c2f0354d816387104333 +size 2399217440 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf new file mode 100644 index 0000000..6a84e67 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f50c69ccfc35471da511f29888498573483f1654aecf91d8ef7221b4b380b2 +size 3784828704 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ3_S.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ3_S.gguf new file mode 100644 index 0000000..a774130 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6823a8f13c0e1b8411885e11295eaaf62f24c5adc5444616055bbcfdcb46e867 +size 3682330400 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a4c8064 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19b46699fc531baa837af4743688286add5ca7aaf69429036579ed63acd381c4 +size 3518752544 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8f0d995 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e144a0dd7b62c103fcced3b9d44355c54af35d8216a0f6ba70598cbfc599c2bf +size 3274917664 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf new file mode 100644 index 0000000..99a6eb4 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259a8df4f84b45dc0c1f717835cf09d50d09776807cd147c7c1d974f20769c9d +size 4677994272 diff --git a/llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf b/llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf new file mode 100644 index 0000000..bb54e7c --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc5ef1572e86674d4ab32d42ae9d0cbd6cb38ba7c91f103457d2e51920aafe5 +size 4447668000 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf b/llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf new file mode 100644 index 0000000..453b33c --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c77cdd350882c75e55572210a38c85a2737a151c14cc58d383900bad054faee8 +size 3179136800 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf b/llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b6877eb --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5050a77a06ea294f26672f9c8a8167b88f74baa5d13f4fc3d9ba0d3cbd9f775 +size 2988820256 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf b/llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c5d1d4f --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4265ebe60e8bd502e1f7871546d2d1f442a36845789095d812a3aefc354e7d70 +size 4321961760 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf b/llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e89fbb7 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e35eae46338a5caccaba21712d2d36cebb7dc9e58e7efac635c0f9b36bae09 +size 4018923296 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf b/llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf new file mode 100644 index 0000000..703227e --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918d6b8ab5bf859be0bedc5be7ea88ef6b5b4071a4516ab523e0420e11ffc3b8 +size 3664504608 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf b/llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf new file mode 100644 index 0000000..ea39999 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376eb6b463b9d3539426b07ee92653f99fa4edf74b698d2fc8b94d432d38a30d +size 4675897120 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf b/llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf new file mode 100644 index 0000000..575be45 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83ce65d0dc49bfc42e5354ed83d198d84e12f4fc9dd56746a73c81a13e32e38 +size 5130258208 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf b/llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf new file mode 100644 index 0000000..79522a2 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4add5230f88dd56efe5fc175ce2de6dd87fc81a47816d1816f7b23f129e7e6 +size 4920739616 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf b/llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a10ffc3 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba5a50dc1587bd409d83d8dfad460300243744eb2494061bddf4c6b19d32940 +size 4692674336 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf b/llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf new file mode 100644 index 0000000..66d5895 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b592765c8fd59beebf25b0417ebdfd8f85d5ddea8893de731af56779a0cf86 +size 5732992800 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf b/llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fe1deb0 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d09d238289c86bc35ca0e52335186cd49777d475f2dbe31f894a425f1a244df +size 5599299360 diff --git a/llama3.1-8B-toucan-full-sft.i1-Q6_K.gguf b/llama3.1-8B-toucan-full-sft.i1-Q6_K.gguf new file mode 100644 index 0000000..1fb5358 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7983ca601f2b496d67870f5c413d06353a0dfd2f40554178d479d240a80047fa +size 6596011808 diff --git a/llama3.1-8B-toucan-full-sft.imatrix.gguf b/llama3.1-8B-toucan-full-sft.imatrix.gguf new file mode 100644 index 0000000..7b27ed9 --- /dev/null +++ b/llama3.1-8B-toucan-full-sft.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9552f52dd5beb65877878dcbdbf21146d1fbc2c6656202a66427fb40f9b3bd7 +size 5015200