commit 3269a5d8e37892aaf66a5c6901902c69c8a20d26 Author: ModelHub XC Date: Tue May 19 07:17:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Salad-4x8B-V2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ccaa90f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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-Salad-4x8B-V2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Salad-4x8B-V2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Salad-4x8B-V2.i1-IQ1_M.gguf b/Llama-Salad-4x8B-V2.i1-IQ1_M.gguf new file mode 100644 index 0000000..8b4d70f --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45531d251b7f91b4bc964a40978a281ecc8ae0dc54012d23bddeee34f4a031e +size 5940519200 diff --git a/Llama-Salad-4x8B-V2.i1-IQ1_S.gguf b/Llama-Salad-4x8B-V2.i1-IQ1_S.gguf new file mode 100644 index 0000000..35a937f --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf392d8ce3462eaa5c215868ceb6d0c972f333e53859a0346b735e1fc0612ae +size 5418328352 diff --git a/Llama-Salad-4x8B-V2.i1-IQ2_M.gguf b/Llama-Salad-4x8B-V2.i1-IQ2_M.gguf new file mode 100644 index 0000000..e4d6d20 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1cf36d937f5ae6daa41362919b8071a88011d61fa6a9b202952208a1680c1a +size 8444395808 diff --git a/Llama-Salad-4x8B-V2.i1-IQ2_S.gguf b/Llama-Salad-4x8B-V2.i1-IQ2_S.gguf new file mode 100644 index 0000000..355a3fe --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb1a91311f90fa2508a0725673224c95477aaa66dffadd9d2abb5f09e8609a9 +size 7748141344 diff --git a/Llama-Salad-4x8B-V2.i1-IQ2_XS.gguf b/Llama-Salad-4x8B-V2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c6fb02b --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c17615ce0d7aff1fe5dfbbc5ce5820866175d746772765a74024d8c0a066cb +size 7523868960 diff --git a/Llama-Salad-4x8B-V2.i1-IQ2_XXS.gguf b/Llama-Salad-4x8B-V2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..84c5f5e --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33792fdb307ae7a67c3088f2c7e1807aaaf346136dffe68439e27c387f372cdf +size 6810837280 diff --git a/Llama-Salad-4x8B-V2.i1-IQ3_M.gguf b/Llama-Salad-4x8B-V2.i1-IQ3_M.gguf new file mode 100644 index 0000000..b5c24cd --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea0802198e2d31927f4c05d5b610dbd578c42cc47a27d1ab37ea3316857ac33 +size 11147141408 diff --git a/Llama-Salad-4x8B-V2.i1-IQ3_S.gguf b/Llama-Salad-4x8B-V2.i1-IQ3_S.gguf new file mode 100644 index 0000000..89b5c90 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02c1834404ed251480c15a2d2c6b6c5d42c413e73b4ee230c457bad7658f639 +size 10951057696 diff --git a/Llama-Salad-4x8B-V2.i1-IQ3_XS.gguf b/Llama-Salad-4x8B-V2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..58c0272 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2528865f20133a38dcbd6927135d9c023f10a9ac381c9802be28fc0dcdd19c97 +size 10391118112 diff --git a/Llama-Salad-4x8B-V2.i1-IQ3_XXS.gguf b/Llama-Salad-4x8B-V2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9e401ff --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13973998118e5ec6d415efdc36560796a2cdae2ae7f9d0f6929d1cec3f93d5e2 +size 9750921504 diff --git a/Llama-Salad-4x8B-V2.i1-IQ4_XS.gguf b/Llama-Salad-4x8B-V2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e738b1d --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbdd089a3a9a65fa3a7d2adf996fff37be4eb83296801ebad9680ebc3c808d2 +size 13433962784 diff --git a/Llama-Salad-4x8B-V2.i1-Q2_K.gguf b/Llama-Salad-4x8B-V2.i1-Q2_K.gguf new file mode 100644 index 0000000..a89e0c6 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb92ee9eadb6cdabace6cf61b156833f768e922f7c4d913bf140c696950a664 +size 9302819104 diff --git a/Llama-Salad-4x8B-V2.i1-Q3_K_L.gguf b/Llama-Salad-4x8B-V2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5b8b726 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5bb663d364dd37e938a77a7aa2b7e51102158b87ce489f1d08960eb1fa440ed +size 13044015392 diff --git a/Llama-Salad-4x8B-V2.i1-Q3_K_M.gguf b/Llama-Salad-4x8B-V2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..85e86e9 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab852edd05faf59f2184c649089c7d2db6d1c3b96a98a9ca2daad47ebe615f3b +size 12080374048 diff --git a/Llama-Salad-4x8B-V2.i1-Q3_K_S.gguf b/Llama-Salad-4x8B-V2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..cf6b4f5 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1b21094aaa1aba925cea268848a6798ae083ec9c58ad63cf02a01ffb2aa023 +size 10933231904 diff --git a/Llama-Salad-4x8B-V2.i1-Q4_0.gguf b/Llama-Salad-4x8B-V2.i1-Q4_0.gguf new file mode 100644 index 0000000..4415c02 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53346d2d8dd4fcbab562393f521b702807f3c11d4229c354b6940bf827140ef7 +size 14234714400 diff --git a/Llama-Salad-4x8B-V2.i1-Q4_K_M.gguf b/Llama-Salad-4x8B-V2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..69cec46 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ed7ed40f5c60e16c1201a7c2b60b9bc709af164f646c67f8f0d7689865f5ed +size 15162179872 diff --git a/Llama-Salad-4x8B-V2.i1-Q4_K_S.gguf b/Llama-Salad-4x8B-V2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6ff0f98 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d41eaa30f539f9288231efcdfd3284347dd2a33fdb0bd8a3e1b880d19c56076 +size 14295531808 diff --git a/Llama-Salad-4x8B-V2.i1-Q5_K_M.gguf b/Llama-Salad-4x8B-V2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..14084d5 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b957d02cb1da3130e0f5b112cd5ffd50c51b75595cbae9ed542a9f07aa2ea0b8 +size 17736040736 diff --git a/Llama-Salad-4x8B-V2.i1-Q5_K_S.gguf b/Llama-Salad-4x8B-V2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ec894be --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46232fa8bd1db7c0e768b58b026111da680fb522199cd6eeae41822d7a9af5a4 +size 17228005664 diff --git a/Llama-Salad-4x8B-V2.i1-Q6_K.gguf b/Llama-Salad-4x8B-V2.i1-Q6_K.gguf new file mode 100644 index 0000000..c520a91 --- /dev/null +++ b/Llama-Salad-4x8B-V2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097ba9d9a5b514a221f1320bb7818adfec7a6a6428e8ac1025a96ae4f54eb650 +size 20470767904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f098cd1 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: HiroseKoichi/Llama-Salad-4x8B-V2 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- nsfw +- not-for-all-audiences +- llama-3 +- text-generation-inference +- moe +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/HiroseKoichi/Llama-Salad-4x8B-V2 + + +static quants are available at https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-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-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ1_S.gguf) | i1-IQ1_S | 5.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ1_M.gguf) | i1-IQ1_M | 6.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ2_S.gguf) | i1-IQ2_S | 7.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ2_M.gguf) | i1-IQ2_M | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q2_K.gguf) | i1-Q2_K | 9.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 11.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ3_S.gguf) | i1-IQ3_S | 11.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ3_M.gguf) | i1-IQ3_M | 11.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q4_0.gguf) | i1-Q4_0 | 14.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 17.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-4x8B-V2-i1-GGUF/resolve/main/Llama-Salad-4x8B-V2.i1-Q6_K.gguf) | i1-Q6_K | 20.6 | 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..4d186e5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f07fb42e001ec1b06d177eeb5882ee31ce447fc744306e6b8eb2d37a231afe5 +size 14164869