commit 9b959b9cd461c5ea6ed3c9ebb7a9767e88d4129d Author: ModelHub XC Date: Thu Jun 18 03:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-experiment-v1-9B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..68a3e6e --- /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 +llama-3-experiment-v1-9B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-experiment-v1-9B.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..a28f33a --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: grimjim/llama-3-experiment-v1-9B +language: +- en +library_name: transformers +license: llama3 +license_link: LICENSE +quantized_by: mradermacher +tags: +- meta +- llama-3 +- pytorch +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/grimjim/llama-3-experiment-v1-9B + + +static quants are available at https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-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-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q2_K.gguf) | i1-Q2_K | 3.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q4_0.gguf) | i1-Q4_0 | 5.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q4_1.gguf) | i1-Q4_1 | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-i1-GGUF/resolve/main/llama-3-experiment-v1-9B.i1-Q6_K.gguf) | i1-Q6_K | 7.4 | 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..2730159 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61d362c2cbf741652365a9cbc04fa72c6375ec358f58932d1bb0e1725587d39 +size 5611681 diff --git a/llama-3-experiment-v1-9B.i1-IQ1_M.gguf b/llama-3-experiment-v1-9B.i1-IQ1_M.gguf new file mode 100644 index 0000000..0f5856c --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ca9a255857f46fca6180e3755d8d8f7a8a00b935f5d9eff4580f43a2cad593 +size 2361335552 diff --git a/llama-3-experiment-v1-9B.i1-IQ1_S.gguf b/llama-3-experiment-v1-9B.i1-IQ1_S.gguf new file mode 100644 index 0000000..f6a9f85 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f42feed0e7d33c4ddb2d4448928f96ea03e2842619e937945f0b5353b373ba4 +size 2200510208 diff --git a/llama-3-experiment-v1-9B.i1-IQ2_M.gguf b/llama-3-experiment-v1-9B.i1-IQ2_M.gguf new file mode 100644 index 0000000..5594cc3 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0250330b658e9ea59bb1e56a5c421bb0d33f810ea0eb08fd1442dbd4c7128e23 +size 3239264000 diff --git a/llama-3-experiment-v1-9B.i1-IQ2_S.gguf b/llama-3-experiment-v1-9B.i1-IQ2_S.gguf new file mode 100644 index 0000000..7665555 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566701c4675d6ae068eae2a93c4ca2e06658d51f29171cc5bb4154644c57e004 +size 3024830208 diff --git a/llama-3-experiment-v1-9B.i1-IQ2_XS.gguf b/llama-3-experiment-v1-9B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..23be1bf --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96964bfe2dcb9811ec562d78773fcc55ad6af45ac9947d978d2ce799047886b5 +size 2862685952 diff --git a/llama-3-experiment-v1-9B.i1-IQ2_XXS.gguf b/llama-3-experiment-v1-9B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..dcad980 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6235f55af4a1668f6910a307989366b83e55ae4ef3ab3821fddd71330435c588 +size 2629377792 diff --git a/llama-3-experiment-v1-9B.i1-IQ3_M.gguf b/llama-3-experiment-v1-9B.i1-IQ3_M.gguf new file mode 100644 index 0000000..42c116f --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb4960339b279e5d7f54370cd6ba009fbd1da2cf5ab88f1deff6fe959c0532c +size 4170964736 diff --git a/llama-3-experiment-v1-9B.i1-IQ3_S.gguf b/llama-3-experiment-v1-9B.i1-IQ3_S.gguf new file mode 100644 index 0000000..830869f --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fec8e9a7681cffaaaab03dc2c5650cc2332a7c54ebfcd855dd0a4ccf97786ec4 +size 4059553536 diff --git a/llama-3-experiment-v1-9B.i1-IQ3_XS.gguf b/llama-3-experiment-v1-9B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..72419c1 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ccbb40144ddde234b169ff4d2761581c859b29357b24ae89b3b68fb9b969a8e +size 3875528448 diff --git a/llama-3-experiment-v1-9B.i1-IQ3_XXS.gguf b/llama-3-experiment-v1-9B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0a7b744 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110fd3b5902436386f3ee22ca8e6456dc286eda1b9a5c6eb586b425d086aa392 +size 3609935616 diff --git a/llama-3-experiment-v1-9B.i1-IQ4_NL.gguf b/llama-3-experiment-v1-9B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..51e8e20 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9f49c1a4f7dffab2f918debbb04278dd61dff7f7862c576ec3f21ce3a78b1e +size 5170953984 diff --git a/llama-3-experiment-v1-9B.i1-IQ4_XS.gguf b/llama-3-experiment-v1-9B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2820f2f --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610306454c2bb90b11b40808346192db6b6540d9103cc513a51f5c30790bc053 +size 4913889024 diff --git a/llama-3-experiment-v1-9B.i1-Q2_K.gguf b/llama-3-experiment-v1-9B.i1-Q2_K.gguf new file mode 100644 index 0000000..befe0e2 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db5d25821313ea9b3a8af8e8c66ea7d372276b6a225d70709cf2494f26a1d7f +size 3500130048 diff --git a/llama-3-experiment-v1-9B.i1-Q2_K_S.gguf b/llama-3-experiment-v1-9B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..1820985 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0063ee5fc9dc84f3b9b4a07fa8c9c0491364bbeaa93076ca01521bb0d3cc6c +size 3279142656 diff --git a/llama-3-experiment-v1-9B.i1-Q3_K_L.gguf b/llama-3-experiment-v1-9B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bf51181 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b799a0f27f9e2408d8d5cc2509a674a847600fc03fec5d9bfd5d02d8eb03f81 +size 4779138816 diff --git a/llama-3-experiment-v1-9B.i1-Q3_K_M.gguf b/llama-3-experiment-v1-9B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..020803c --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a549c4ccdc364642bc769717f49a0b4f9007bb94a17d9b211e9e87bdc649289 +size 4436254464 diff --git a/llama-3-experiment-v1-9B.i1-Q3_K_S.gguf b/llama-3-experiment-v1-9B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2ac7074 --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f09e7f446735ea2081e43257187883abd55d268150640af1a66b5782674655 +size 4039499520 diff --git a/llama-3-experiment-v1-9B.i1-Q4_0.gguf b/llama-3-experiment-v1-9B.i1-Q4_0.gguf new file mode 100644 index 0000000..8f9413b --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d9a5fae3c1ca7bd24c5f140205c45414323fb62b9db6b80db5df265a79148e +size 5166759680 diff --git a/llama-3-experiment-v1-9B.i1-Q4_1.gguf b/llama-3-experiment-v1-9B.i1-Q4_1.gguf new file mode 100644 index 0000000..cfa4f9c --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f12b36ed19a49608faeedfd3a4fa59dc83386328e70e225d6f271708f76e3b0 +size 5675646720 diff --git a/llama-3-experiment-v1-9B.i1-Q4_K_M.gguf b/llama-3-experiment-v1-9B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b517f9b --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f9b33ab3b0a258fe93cc4e8904a53c472af78e21a7239a42138d1c1be4a8780 +size 5444042496 diff --git a/llama-3-experiment-v1-9B.i1-Q4_K_S.gguf b/llama-3-experiment-v1-9B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e37b55f --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0908d3a15b00a1f6316ea2431f02df3a69a45bdcd86f67c62da189c34b87051 +size 5183536896 diff --git a/llama-3-experiment-v1-9B.i1-Q5_K_M.gguf b/llama-3-experiment-v1-9B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..00e53bf --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b759977df942b79c51af17e88f89c39cbb10a3dd7212e2809659e1d9bd0d74bf +size 6349618944 diff --git a/llama-3-experiment-v1-9B.i1-Q5_K_S.gguf b/llama-3-experiment-v1-9B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..21d857c --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7ebac2c2aec7bae3ddd4d736b3cb611e4dc0c08fa27478ef153a18523ff1f8 +size 6199213824 diff --git a/llama-3-experiment-v1-9B.i1-Q6_K.gguf b/llama-3-experiment-v1-9B.i1-Q6_K.gguf new file mode 100644 index 0000000..8ec1e1e --- /dev/null +++ b/llama-3-experiment-v1-9B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b7741e4474373571d72884c2c24bc340a150bd5463a03ab8a746f975b447d4 +size 7311793920