commit 4dbf0c4148f42a359a1a3ce320f7b217d85e4595 Author: ModelHub XC Date: Wed May 13 05:19:33 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a12a88c --- /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-3-8B-Uncensored-0.5.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Uncensored-0.5.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ1_M.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ1_M.gguf new file mode 100644 index 0000000..4d76d1b --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6018fac2ca1ac2c0b527a287957cf023fdf5040188aaf76c1ea6f50080042d +size 2161973696 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ1_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ1_S.gguf new file mode 100644 index 0000000..8e6bcda --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b987a96873b0f5957c1b56066584993c413fc5324c49a8b4dedcab635ef244d +size 2019629504 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ2_M.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ2_M.gguf new file mode 100644 index 0000000..2caf9af --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c68ef332bf6e2e49064329a0c0d636ccaecf1bf0b44967a3b2ee563aef546fa +size 2948282816 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ2_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ2_S.gguf new file mode 100644 index 0000000..8271ccc --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134f17a864bcb7e4385f55a2e6199f58aa4758cbc8b28050588b873c79870eb8 +size 2758490560 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ2_XS.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f1c8212 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d324c52aa6240d0cfe4e6b7c611055fc9e9f8b2684de1a8c9a934e6c3c25eb0 +size 2605783488 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ2_XXS.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5081f2c --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d22da59bed365b45ad64fc71bd9b3f83e6063c98a1a3229e9e47ade85da4dd0 +size 2399214016 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ3_M.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ3_M.gguf new file mode 100644 index 0000000..d1ca074 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61ee19e0cb8d81e4f9428be2f3b9b20c618edfbff4691312d242eaaaeb7549d +size 3784825280 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ3_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ3_S.gguf new file mode 100644 index 0000000..c3c08de --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfaa4fde2fba109c736e3d5e770173fb254046d442a6216743dea78aa7b2311 +size 3682326976 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ3_XS.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ3_XS.gguf new file mode 100644 index 0000000..89d1248 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47f1f06897b729f9ad9f835d039f174402a2fe863a6fbaa58aa20d1705261d8 +size 3518749120 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ3_XXS.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b7e448b --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23f866f97734960acd619e4e1c6dd4031e36d979edf8a6e2d1163d13a679c802 +size 3274914240 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ4_NL.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a474bf3 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ccfd9baa4224841e93f53e1b01c012a729fac6c9af52c142135c04c97960826 +size 4677990848 diff --git a/Llama-3-8B-Uncensored-0.5.i1-IQ4_XS.gguf b/Llama-3-8B-Uncensored-0.5.i1-IQ4_XS.gguf new file mode 100644 index 0000000..03239a0 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c154bd33fe2ef4783844643e8b4d99fb2edf887122bce7caf0596f5b61e89031 +size 4447664576 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q2_K.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q2_K.gguf new file mode 100644 index 0000000..8c9c40a --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1ac124de4cb0d2e83b8da858b5d97cc9e9f4b89e2963a3f3bc604cd6a27bb6 +size 3179133376 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q2_K_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q2_K_S.gguf new file mode 100644 index 0000000..22e6053 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7beee4784dc3d9da9ea791173515c8cd4dd34e8b76bced179e3f058c6d25c832 +size 2988816832 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q3_K_L.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0d82e2d --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23437098e636b6893924b03601ca291ee3a0985b5fab252fa760bbbc6272f5ae +size 4321958336 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q3_K_M.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f0f621c --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7298449ffebcb751618cd9b48a101165b371685efe8aaf8a1720030d76a2635 +size 4018919872 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q3_K_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c79cbf2 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1dffe54958a5ffafb70099b649d7c0c588de813d3339ce0b4899bea9811cb90 +size 3664501184 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q4_0.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q4_0.gguf new file mode 100644 index 0000000..5598604 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e3a98cd8f9f687c57ba65ed3acc5731dc0721c61883eda88c30b521c13fc06 +size 4675893696 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q4_1.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q4_1.gguf new file mode 100644 index 0000000..e3da066 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90639f935954b1ec29850403073cf364d1acb4e9723788b92b79001578d43e1 +size 5130254784 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q4_K_M.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d9b8054 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98605af46a1eb34bf91e854b6813c3a51d8519d9bc7b2bf409ff5124b8bfe440 +size 4920736192 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q4_K_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q4_K_S.gguf new file mode 100644 index 0000000..280d6e2 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ec8ecca2ccb695c1a2228aacfce5f9c849b0ec900d97b455474b1fe2e8b0e9 +size 4692670912 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q5_K_M.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d168997 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7289594c9d5444fd56a995902f9eb510a6ed543f992462e4373300617ee213de +size 5732989376 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q5_K_S.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q5_K_S.gguf new file mode 100644 index 0000000..24c4476 --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fde5f36186354a2f1ccbab8d470a7ead829fd3e18f01ee6687aac35abc9fbc3 +size 5599295936 diff --git a/Llama-3-8B-Uncensored-0.5.i1-Q6_K.gguf b/Llama-3-8B-Uncensored-0.5.i1-Q6_K.gguf new file mode 100644 index 0000000..681bbba --- /dev/null +++ b/Llama-3-8B-Uncensored-0.5.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3be68f76b199100066e0ac285dec74bdfbee4c84b965bcc5482f2dd63faa85f +size 6596008384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..afa5dc5 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: MrRobotoAI/Llama-3-8B-Uncensored-0.5 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/MrRobotoAI/Llama-3-8B-Uncensored-0.5 + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-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-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Uncensored-0.5-i1-GGUF/resolve/main/Llama-3-8B-Uncensored-0.5.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..47aba58 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a937879cc5eb7285555676e2e43a9aef1904c93425b0144d6bacdb2515215b2e +size 4988157