commit 2e328a8e89091d0dad7dbf3fc2ea1fb95dbddb46 Author: ModelHub XC Date: Tue May 19 05:28:06 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f408a2 --- /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 +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_M.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_M.gguf new file mode 100644 index 0000000..29eea85 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae88d32ec6ae1846e4ded44edee574c7947449d5b20d8c4ce8c86eba000cc335 +size 2161972224 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_S.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_S.gguf new file mode 100644 index 0000000..e58c9a5 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7cb63a5fd68a7868b5632415dae02ad6fbf09da2627700de904a8846f67300 +size 2019628032 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_M.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_M.gguf new file mode 100644 index 0000000..ce16ab6 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b06f2710a942de355acf8693c18918a0457ba48bacd7d0899659507d56f388 +size 2948281344 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_S.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_S.gguf new file mode 100644 index 0000000..ea0d922 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:775446abe06240d42e94fcd24ca259ddb0bd2db51b563660b8eb49d44943adaa +size 2758489088 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XS.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b18762f --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181ac53d62549924deac404918d3af93e6fa922a573b543ab9335c0fc29c20b3 +size 2605782016 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XXS.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..97c4055 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7102320c8c88139865dacdecd5ed394df6477a23818b97f74cd45beb3e36f93 +size 2399212544 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_M.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_M.gguf new file mode 100644 index 0000000..38c2412 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:229b441ade869dadf7e7dd4dd6808caae2b8b5ad8716ce49cca888fc6f965433 +size 3784823808 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_S.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_S.gguf new file mode 100644 index 0000000..f7021d8 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ef1ba6c7c403fd94a457f8f5b7f15daaa6eda846fc0cfa5e16bbd2efed342b +size 3682325504 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XS.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XS.gguf new file mode 100644 index 0000000..16fc17b --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2582125adde78255528a92732c65774f1a67a90935a23e82817b775ab406c935 +size 3518747648 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XXS.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3a563ae --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f9e5d7ba5387156cc64d7d9a633a867fc4b4277bbe9e1c9b8d54c76aceb1292 +size 3274912768 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ4_XS.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ab21a60 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d484c322687ef5de6f71b39ad5cc6b9037927017fa89c6dce8b823567b05f39 +size 4447663104 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q2_K.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q2_K.gguf new file mode 100644 index 0000000..5d159c4 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d90689ae65365d9bf5044ac8684cf4f10a765928bd117cbec6da835c0f761d +size 3179131904 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_L.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c8d4759 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464d54b703587b1bc43880c63cc21a146fbb17921d4d2e3271fbe8db73a390b8 +size 4321956864 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_M.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6063cb0 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4bca79c23ccb96881b61f6466a8b3a973dbcd9879a09fac059059fbb4400dc +size 4018918400 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_S.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_S.gguf new file mode 100644 index 0000000..bce67c9 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83f6bc8402aaa307cdd78ecc2266d07bd9ab4c61b3bb1680811669847f12ff3 +size 3664499712 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_0.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_0.gguf new file mode 100644 index 0000000..945a612 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73670d59eaad484be0c0bf89649728b43b8385bb03592d14fd03212ee65aeeed +size 4675892224 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_M.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0f1ebd3 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04cc7f47773789c8578ba2ba8b9cc738ac9b1f4bc3d7adf796b209acf9ebd856 +size 4920734720 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_S.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_S.gguf new file mode 100644 index 0000000..243bdb5 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cecf2056c634034d71500a354f1df9f1c7574de687933b756d77c721293db5b5 +size 4692669440 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_M.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_M.gguf new file mode 100644 index 0000000..fddd4e9 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7efb2cd08b11953e7de6c7c0c08c3cafa7b47375fb058e320fdacee283d8ff9 +size 5732987904 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_S.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_S.gguf new file mode 100644 index 0000000..eb99941 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c0aef1feebc4a247334e31f8b9fbb616157916ea40912cd16d1a97eb086be1 +size 5599294464 diff --git a/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q6_K.gguf b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q6_K.gguf new file mode 100644 index 0000000..2c62d83 --- /dev/null +++ b/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6135a627868b43731d057c2c7250cb5b6050b5e3ba47bfac507ef0085292529 +size 6596006912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..36dcb89 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: saishf/Long-Neural-SOVLish-Devil-8B-L3-262K +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/saishf/Long-Neural-SOVLish-Devil-8B-L3-262K + + +static quants are available at https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-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/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF/resolve/main/Long-Neural-SOVLish-Devil-8B-L3-262K.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..03b15f2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3188c0dd42f937ecb518ead4cb14466f4784d4d6102c956e55465bbe4913bd +size 4988143