commit 31bd19c108bcf071b0a5d4cc1feb22e6073d0512 Author: ModelHub XC Date: Fri Jul 17 17:42:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Athena-m-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a3e3e5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +L3.1-Athena-m-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-m-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Athena-m-8B.IQ4_XS.gguf b/L3.1-Athena-m-8B.IQ4_XS.gguf new file mode 100644 index 0000000..4b2b9f2 --- /dev/null +++ b/L3.1-Athena-m-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f0c4af06722db1b2848cebe8e41df4fad090504d161c20c6033aa3fba7aeb99 +size 4484370560 diff --git a/L3.1-Athena-m-8B.Q2_K.gguf b/L3.1-Athena-m-8B.Q2_K.gguf new file mode 100644 index 0000000..f24a5d1 --- /dev/null +++ b/L3.1-Athena-m-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83dc50314b2b801a5ad29af15ac055d4c7fd8c0304833f7f152fc9db15564b05 +size 3179139200 diff --git a/L3.1-Athena-m-8B.Q3_K_L.gguf b/L3.1-Athena-m-8B.Q3_K_L.gguf new file mode 100644 index 0000000..a1ae79f --- /dev/null +++ b/L3.1-Athena-m-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2bbd7ed79d3089475ede4d6418bbc115f5e78f3be1347f1823309d6c0a79e3 +size 4321964160 diff --git a/L3.1-Athena-m-8B.Q3_K_M.gguf b/L3.1-Athena-m-8B.Q3_K_M.gguf new file mode 100644 index 0000000..f4de173 --- /dev/null +++ b/L3.1-Athena-m-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90823fee822250b872ab847f37bd6fbe197d1b65b7f74316674dde7114681b17 +size 4018925696 diff --git a/L3.1-Athena-m-8B.Q3_K_S.gguf b/L3.1-Athena-m-8B.Q3_K_S.gguf new file mode 100644 index 0000000..a7404ce --- /dev/null +++ b/L3.1-Athena-m-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35b0a827fed546a221b888ed918197a77bb46db6dcffeb1b8622614b3f218b3 +size 3664507008 diff --git a/L3.1-Athena-m-8B.Q4_K_M.gguf b/L3.1-Athena-m-8B.Q4_K_M.gguf new file mode 100644 index 0000000..c1b070a --- /dev/null +++ b/L3.1-Athena-m-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8177540c9cf465c7520c84c23b61f8f5aa64a771a338ed0678aa087fb7826d +size 4920742016 diff --git a/L3.1-Athena-m-8B.Q4_K_S.gguf b/L3.1-Athena-m-8B.Q4_K_S.gguf new file mode 100644 index 0000000..5ed9eea --- /dev/null +++ b/L3.1-Athena-m-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0073d4ecd56aa76382514cf125f79288c9363bc80693ad58f3b73111ba594961 +size 4692676736 diff --git a/L3.1-Athena-m-8B.Q5_K_M.gguf b/L3.1-Athena-m-8B.Q5_K_M.gguf new file mode 100644 index 0000000..a4618c6 --- /dev/null +++ b/L3.1-Athena-m-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8440124372b9b8d17b78676f63e3007ac23fa5f91986fd7065f388c475d1c65 +size 5732995200 diff --git a/L3.1-Athena-m-8B.Q5_K_S.gguf b/L3.1-Athena-m-8B.Q5_K_S.gguf new file mode 100644 index 0000000..8f2cd67 --- /dev/null +++ b/L3.1-Athena-m-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23746c2c709112099792cb16e7a3c391a1412856c2cb05b2d2e9837598e3c344 +size 5599301760 diff --git a/L3.1-Athena-m-8B.Q6_K.gguf b/L3.1-Athena-m-8B.Q6_K.gguf new file mode 100644 index 0000000..4c2b741 --- /dev/null +++ b/L3.1-Athena-m-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8cd912d6ccc3dd6e9502f7e262433861596d4fae78fb67f8b6352bd273d90b +size 6596014208 diff --git a/L3.1-Athena-m-8B.Q8_0.gguf b/L3.1-Athena-m-8B.Q8_0.gguf new file mode 100644 index 0000000..9b84831 --- /dev/null +++ b/L3.1-Athena-m-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275d1e389931810f9f87c4fe14f6e28c32cccb1bca8f5b868fe65628e626f507 +size 8540778624 diff --git a/L3.1-Athena-m-8B.f16.gguf b/L3.1-Athena-m-8B.f16.gguf new file mode 100644 index 0000000..fdff517 --- /dev/null +++ b/L3.1-Athena-m-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2872d3a425293d74b958ed46b8ff28d8b5f05b40896edfb84029b7b1482583b7 +size 16068898944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..82bd1e3 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mergekit-community/L3.1-Athena-m-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/L3.1-Athena-m-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.1-Athena-m-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3.1-Athena-m-8B-i1-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/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-m-8B-GGUF/resolve/main/L3.1-Athena-m-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +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. + +