commit cca258b35c87694644473fae7c14c8fa06b3ebb4 Author: ModelHub XC Date: Wed Oct 21 21:44:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MN-12B-Lyra-v4-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49d0411 --- /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 +MN-12B-Lyra-v4.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Lyra-v4.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MN-12B-Lyra-v4.i1-IQ1_M.gguf b/MN-12B-Lyra-v4.i1-IQ1_M.gguf new file mode 100644 index 0000000..2fcb17a --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b817d51fa166fcc36c4cfc40fc55c5a4a7ec2c100f99aad0b22523efc0b495 +size 3221628032 diff --git a/MN-12B-Lyra-v4.i1-IQ1_S.gguf b/MN-12B-Lyra-v4.i1-IQ1_S.gguf new file mode 100644 index 0000000..e5ab61c --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebada7cba2f7381b6ac0498676ac7b7b00c51e91076e67ab2f0a9d7cdf498126 +size 2999215232 diff --git a/MN-12B-Lyra-v4.i1-IQ2_M.gguf b/MN-12B-Lyra-v4.i1-IQ2_M.gguf new file mode 100644 index 0000000..c040c85 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32edc58d60987f9f327911bfdb571aafd010c590e165a657ee5d853e388d27a7 +size 4435027072 diff --git a/MN-12B-Lyra-v4.i1-IQ2_S.gguf b/MN-12B-Lyra-v4.i1-IQ2_S.gguf new file mode 100644 index 0000000..8ac6d21 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db97909ecffa9f043952397747af7d59a38ef7d466201f390d1032d809671c07 +size 4138476672 diff --git a/MN-12B-Lyra-v4.i1-IQ2_XS.gguf b/MN-12B-Lyra-v4.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1227949 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932fd1a1e50208466ee667efba2f6f9d2b5d4eb08c00148fa88574ef38b73d11 +size 3915080832 diff --git a/MN-12B-Lyra-v4.i1-IQ2_XXS.gguf b/MN-12B-Lyra-v4.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..62cd358 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc782c21341e5e1dbb12167c212a516a13bdf688230b8d8260ee62391d48a398 +size 3592316032 diff --git a/MN-12B-Lyra-v4.i1-IQ3_M.gguf b/MN-12B-Lyra-v4.i1-IQ3_M.gguf new file mode 100644 index 0000000..c055cda --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edfa1f71e7467d5f5c6497bc9028706507d55dc5726b88d93ab33a7fd3edda5f +size 5722236032 diff --git a/MN-12B-Lyra-v4.i1-IQ3_S.gguf b/MN-12B-Lyra-v4.i1-IQ3_S.gguf new file mode 100644 index 0000000..4f3c727 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53cf639b2e01c663cd5e2378800b8fa4b348dc4513e5cdc86bcb98781004dc7 +size 5562082432 diff --git a/MN-12B-Lyra-v4.i1-IQ3_XS.gguf b/MN-12B-Lyra-v4.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2ae5237 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc60d0c0e4f239b3913927edbfb575c02ce3ff683ed8cca6ff60f0b337a1aa3e +size 5306492032 diff --git a/MN-12B-Lyra-v4.i1-IQ3_XXS.gguf b/MN-12B-Lyra-v4.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..89efd9f --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d536de0c66a313dd0316a6519253cf9cac8dabcdcf8b6953092ca7a752ecddb5 +size 4945388672 diff --git a/MN-12B-Lyra-v4.i1-IQ4_XS.gguf b/MN-12B-Lyra-v4.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d375a89 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf4efad9f67b710006dc5d87c0bb335b7a9595384989b51ed710afa787553cc +size 6742713472 diff --git a/MN-12B-Lyra-v4.i1-Q2_K.gguf b/MN-12B-Lyra-v4.i1-Q2_K.gguf new file mode 100644 index 0000000..87a0a24 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d270c88dc24908bb868f5155a0c419f54a624a192bb1ed6a236606a1c36d6a8 +size 4791051392 diff --git a/MN-12B-Lyra-v4.i1-Q3_K_L.gguf b/MN-12B-Lyra-v4.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a04d5e7 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184382fbec4ca7622452c0a590b3fa0d615d739675f52f1e00c97a211a8fc205 +size 6561506432 diff --git a/MN-12B-Lyra-v4.i1-Q3_K_M.gguf b/MN-12B-Lyra-v4.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4f18654 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56b331409ef88cfffcb5fd11a3532511955069e88fdf9f1c29105b4409b635d +size 6083093632 diff --git a/MN-12B-Lyra-v4.i1-Q3_K_S.gguf b/MN-12B-Lyra-v4.i1-Q3_K_S.gguf new file mode 100644 index 0000000..718eccb --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae60bbd80b340aabd22f43fcad014ab4a5cf7ed8beb3657f4843e2e49702380 +size 5534229632 diff --git a/MN-12B-Lyra-v4.i1-Q4_0.gguf b/MN-12B-Lyra-v4.i1-Q4_0.gguf new file mode 100644 index 0000000..e239fd3 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85bec4572090c9e82fd51fbfd44cdce6131e4aa1e3a5fd3408ac8647a55b8d7 +size 7094641792 diff --git a/MN-12B-Lyra-v4.i1-Q4_K_M.gguf b/MN-12B-Lyra-v4.i1-Q4_K_M.gguf new file mode 100644 index 0000000..afa53bb --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801a11574ff5fd021320a20315213dffc3e663e1b87ba3ba181da3851c0a3595 +size 7477208192 diff --git a/MN-12B-Lyra-v4.i1-Q4_K_S.gguf b/MN-12B-Lyra-v4.i1-Q4_K_S.gguf new file mode 100644 index 0000000..afa3174 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b14ceba0dfe33e252c8fb73b4f3a9856a7eebe455595a1ef1a61df6e11c1181 +size 7120200832 diff --git a/MN-12B-Lyra-v4.i1-Q5_K_M.gguf b/MN-12B-Lyra-v4.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ca80355 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fec92829c582b0fff120b110f5dfe950e48b8b0f020f2f0a93d82fcfd38d4824 +size 8727635072 diff --git a/MN-12B-Lyra-v4.i1-Q5_K_S.gguf b/MN-12B-Lyra-v4.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7b2e23c --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fd1f029118ed8cd2334e35f8bac0831153a288555f94f230017844543139a7 +size 8518739072 diff --git a/MN-12B-Lyra-v4.i1-Q6_K.gguf b/MN-12B-Lyra-v4.i1-Q6_K.gguf new file mode 100644 index 0000000..efe8ba9 --- /dev/null +++ b/MN-12B-Lyra-v4.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4701e887db78572c26b55489df3fd9d4dd56fd0e74fba0ccf6c098e2e6081d8f +size 10056213632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..494707f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Sao10K/MN-12B-Lyra-v4 +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Sao10K/MN-12B-Lyra-v4 + + +static quants are available at https://huggingface.co/mradermacher/MN-12B-Lyra-v4-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/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Lyra-v4-i1-GGUF/resolve/main/MN-12B-Lyra-v4.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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..431e83a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8af772e17f7120d0851dd249affd84d62ac59b5a994f85518b4a25038cb4ed +size 7054405