commit f9560a935140cf8acb010bdf7afa8f554308aa6d Author: ModelHub XC Date: Fri Jun 19 02:28:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e27257 --- /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 +naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v0.4.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..0ef4c06 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: NAPS-ai/naps-llama-3_1-8b-instruct-v0.4 +datasets: +- MarkrAI/KOpen-HQ-Hermes-2.5-60K +language: +- ko +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/NAPS-ai/naps-llama-3_1-8b-instruct-v0.4 + + +static quants are available at https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-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/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v0.4-i1-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v0.4.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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..a72a7af --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061484ef20f0c3f0d44e38347ebc57727076210c0c650e55d13ad408014c3e1c +size 4988157 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_M.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_M.gguf new file mode 100644 index 0000000..4c4d54a --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9614603b018e11b9a0856e5f28f35a4b909f24f2b5c063093f18f0bfbc824aa1 +size 2161977600 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_S.gguf new file mode 100644 index 0000000..61139cf --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53b147d3a5f33f681ca764d9039d59a2542786d8e1de75b98ba5d909c50cc59 +size 2019633408 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_M.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_M.gguf new file mode 100644 index 0000000..23410e7 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b90546b8f6397ea9874371658e0aee3655d46c1cb16e50ef64a103432b38abb +size 2948286720 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_S.gguf new file mode 100644 index 0000000..c085d71 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5047c6a7e15417bdd5a811df4f128f37a193937ce7b98a0584fc5cbb6153f354 +size 2758494464 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XS.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XS.gguf new file mode 100644 index 0000000..176f771 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5347d17d14931ed033b23f0d0ae5e134aebc17dd049b66b6ae5d42963d206f1 +size 2605787392 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XXS.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..167d4df --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79cb34c6ea27931fb8d4cb2024a0e6e9a293c5e715a2d3bfa6b08aa61fe7e87c +size 2399217920 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_M.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_M.gguf new file mode 100644 index 0000000..eb71572 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6efb9899189f508e34d39d85e8794cb2a20a305c63cfc87e63a157bc6425a3a6 +size 3784829184 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_S.gguf new file mode 100644 index 0000000..7a9d801 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1469305d5539c3daa6017f455aee1d8dcf183b029632d117cfa4bd6a3ba2d450 +size 3682330880 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XS.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cc5465c --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801cc18ebc48278bbdddba2e537c95eae487a36cfb8a7d02cb544a82474cab32 +size 3518753024 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XXS.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a4afa3e --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f06ff0562ec328c662e3618a25d2329deb6791dd8f3c2dfb0e006001be85d0 +size 3274918144 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_NL.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_NL.gguf new file mode 100644 index 0000000..0638113 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3c0337d8e8ec758aa1e2fd8e2132303e7644204703cdf8d403e6353302090f +size 4677994752 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_XS.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_XS.gguf new file mode 100644 index 0000000..764f04b --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12963312eaaa0eefa1bd837e7e0a0767568d1b20edc63795504e4c130ae2d1be +size 4447668480 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K.gguf new file mode 100644 index 0000000..a7c6d40 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9766b4036a7a08b513a9316b08585e9d532f07826c17e519bede5c28f4bd0eb9 +size 3179137280 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9555263 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7799eaa380afb2c25bcb436f2a96a21a5c3e57a01620db2124e66b0a2a3017 +size 2988820736 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_L.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_L.gguf new file mode 100644 index 0000000..49bfdf4 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f20d731add368f4258ddeb4afda531d1166f68fc7cb50c40173f608f37c234 +size 4321962240 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_M.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_M.gguf new file mode 100644 index 0000000..790a622 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4915b3310770d5ecff8bad8b268d9ff24d791559addea7a85696f844a6fd32ae +size 4018923776 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a1cc0a3 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c2d49190b4ec419e311db9357d71fd7b75bc0f8779273d10fbdbe8175203d1 +size 3664505088 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_0.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_0.gguf new file mode 100644 index 0000000..a878fa0 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2661d4db3f17801e0e8c93b41413f453915cceeecaebb78e557b5c142cc80dc +size 4675897600 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_1.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_1.gguf new file mode 100644 index 0000000..c23cfac --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906f310909315b7d5833354ba3f9ff6baf19dc7336da0bd6276b33867694ff9f +size 5130258688 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_M.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_M.gguf new file mode 100644 index 0000000..fd70b1c --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9260fe22d7830d7fbb3c0656811636b5092b0a852c83b7e65a8231db8b391f +size 4920740096 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c6018d6 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db4a7bb34f1fd5def8eb0b78f2d0176b379d39265e076c5cd7159c623b2e234 +size 4692674816 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_M.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e66128b --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ca1422289d96d1bbd46927491a993e5239fc9c4bbe60c0d0c499c24c651422 +size 5732993280 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_S.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_S.gguf new file mode 100644 index 0000000..897350e --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90672bb30b00893d0e6501e75ba292f4c1a6ef27153742082c9410f76224163a +size 5599299840 diff --git a/naps-llama-3_1-8b-instruct-v0.4.i1-Q6_K.gguf b/naps-llama-3_1-8b-instruct-v0.4.i1-Q6_K.gguf new file mode 100644 index 0000000..44f9721 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v0.4.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac7b299230f0074a23b2b6117c6ea168a72d279b4082a039cde26001ce8eba6 +size 6596012288