commit dedb29b5c4b5121bc4ebfe68a9040ae2eb5c2b56 Author: ModelHub XC Date: Thu Jun 18 19:48:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mini-magnum-12b-v1.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3a0a7c --- /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 +mini-magnum-12b-v1.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +mini-magnum-12b-v1.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a4f734e --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: intervitens/mini-magnum-12b-v1.1 +language: +- en +- fr +- de +- es +- it +- pt +- ru +- zh +- ja +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/intervitens/mini-magnum-12b-v1.1 + + +static quants are available at https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-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/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-i1-GGUF/resolve/main/mini-magnum-12b-v1.1.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..125f1b0 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfc6323c2cce42af0704586f8a83eee217cfb3bdf30c7a40e83d87e11837299 +size 7054405 diff --git a/mini-magnum-12b-v1.1.i1-IQ1_M.gguf b/mini-magnum-12b-v1.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..9d5ac58 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d7278f0f460ca4b284ea6882269e9f9210146aeb1aef40a51f224e2895383b +size 3221629856 diff --git a/mini-magnum-12b-v1.1.i1-IQ1_S.gguf b/mini-magnum-12b-v1.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..3ee7226 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e69bd9841010d2915ecf788a845c2ba8772e49c0458ed6ef33c26a8fa9e2377 +size 2999217056 diff --git a/mini-magnum-12b-v1.1.i1-IQ2_M.gguf b/mini-magnum-12b-v1.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..95d8972 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e12c537ee4c560c0566dba51b10bf3703737ae4328fbb38b844b1ca26f9a1f +size 4435029408 diff --git a/mini-magnum-12b-v1.1.i1-IQ2_S.gguf b/mini-magnum-12b-v1.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..efebf41 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894dc73a16d4c93e9d0eb0959fbabbe2eff486c11113be7c0eef4706606bda5d +size 4138479008 diff --git a/mini-magnum-12b-v1.1.i1-IQ2_XS.gguf b/mini-magnum-12b-v1.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..076ff06 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c4a515980855b6238636c60b932ca700f465c9548f728c1bb0d507043f6c0b +size 3915082656 diff --git a/mini-magnum-12b-v1.1.i1-IQ2_XXS.gguf b/mini-magnum-12b-v1.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fe0515e --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b237111a63410943d30a573766ceb175e1b8446e6f5c68c8113730ed8ea4d78 +size 3592317856 diff --git a/mini-magnum-12b-v1.1.i1-IQ3_M.gguf b/mini-magnum-12b-v1.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..380a6f9 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a68eee0b80799a97f1acccc53f5049f54653675ae8abe30a5283d5cdfcc978b +size 5722239072 diff --git a/mini-magnum-12b-v1.1.i1-IQ3_S.gguf b/mini-magnum-12b-v1.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..33a9a7d --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dab27f1776228302d98066dc1b3f0ebb2dfaf29c0076cb2179ba5c6817f20e7 +size 5562085472 diff --git a/mini-magnum-12b-v1.1.i1-IQ3_XS.gguf b/mini-magnum-12b-v1.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4f3d139 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a41947c30cb0d6cabf4697b8101aa6a0fe2f83a055c38ad0d8f2a7a72b6198d +size 5306495072 diff --git a/mini-magnum-12b-v1.1.i1-IQ3_XXS.gguf b/mini-magnum-12b-v1.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f9c73e6 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4046d106a5bbecbb09205e03ff9b44bea8984549f604b8cd845fcc814e35955 +size 4945391008 diff --git a/mini-magnum-12b-v1.1.i1-IQ4_XS.gguf b/mini-magnum-12b-v1.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ece8e27 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617c1baf4b410f06a9e4b1e1727e4b392e901abca830539744b8b6588490e8e6 +size 6742717024 diff --git a/mini-magnum-12b-v1.1.i1-Q2_K.gguf b/mini-magnum-12b-v1.1.i1-Q2_K.gguf new file mode 100644 index 0000000..7275766 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c317bd785a3254df9e052d814f1658191254d7858e65c2651f18fba0c23c456 +size 4791053920 diff --git a/mini-magnum-12b-v1.1.i1-Q3_K_L.gguf b/mini-magnum-12b-v1.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4432d0e --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5070cf7f920c13dca161b92013451d4cf1316d6847ab786f2d9989f21c4be52f +size 6561509472 diff --git a/mini-magnum-12b-v1.1.i1-Q3_K_M.gguf b/mini-magnum-12b-v1.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ea6fed2 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea2eeb65d67305fcb2599983248fa749323913bba9d0fbf58ac1c916d4046aec +size 6083096672 diff --git a/mini-magnum-12b-v1.1.i1-Q3_K_S.gguf b/mini-magnum-12b-v1.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..365df20 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f0cdbcc6d8d3e1efb4acfbff354571d91c2ccc72c969a7be7a48e82cc563bf +size 5534232672 diff --git a/mini-magnum-12b-v1.1.i1-Q4_0.gguf b/mini-magnum-12b-v1.1.i1-Q4_0.gguf new file mode 100644 index 0000000..cd98f85 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:759d277c8a0af769ba93131c79562687883aeb8c843cc1b87f5d7d5a55495fd5 +size 7094645504 diff --git a/mini-magnum-12b-v1.1.i1-Q4_K_M.gguf b/mini-magnum-12b-v1.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7a4d071 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed53e381760dd36c75762265135812f0f6a1ad9e1cafed2002d18baf170b043f +size 7477211904 diff --git a/mini-magnum-12b-v1.1.i1-Q4_K_S.gguf b/mini-magnum-12b-v1.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0666b3f --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce7f2cf26a9ff333fa640c2b9bf6874b179d992c97b31e299d276ac499b9de9 +size 7120204544 diff --git a/mini-magnum-12b-v1.1.i1-Q5_K_M.gguf b/mini-magnum-12b-v1.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..609f44f --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e8cd776e9b92105b8ea276e88e66f2c40f833e5769076ab9cbe0c1a6121fc4c +size 8727639424 diff --git a/mini-magnum-12b-v1.1.i1-Q5_K_S.gguf b/mini-magnum-12b-v1.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ee7a679 --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d99c8a72b3ddfe3dc6e7713bb35aa54d1e6cd85d6bba20bbb8f18bb949de9c5 +size 8518743424 diff --git a/mini-magnum-12b-v1.1.i1-Q6_K.gguf b/mini-magnum-12b-v1.1.i1-Q6_K.gguf new file mode 100644 index 0000000..2642afe --- /dev/null +++ b/mini-magnum-12b-v1.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b701c1513f43a8a053692d57b23e88e3f4e556b3d6795e367efc94c222174d3 +size 10056218688