commit 21323e22cafb73dd189d7c99b35c26a0fb91ec10 Author: ModelHub XC Date: Thu Jun 11 10:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Athena-b-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f576efa --- /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-b-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-b-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Athena-b-8B.IQ4_XS.gguf b/L3.1-Athena-b-8B.IQ4_XS.gguf new file mode 100644 index 0000000..dbba7d5 --- /dev/null +++ b/L3.1-Athena-b-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda8078a4463770f21f8f89ccf4935968a2355fc8c8d3411abc294e46b79d51a +size 4484370496 diff --git a/L3.1-Athena-b-8B.Q2_K.gguf b/L3.1-Athena-b-8B.Q2_K.gguf new file mode 100644 index 0000000..33165ef --- /dev/null +++ b/L3.1-Athena-b-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ebc0dd7ac52c514a578018c316980b473a591f901c57cbb28dbdd1237cd520c +size 3179139136 diff --git a/L3.1-Athena-b-8B.Q3_K_L.gguf b/L3.1-Athena-b-8B.Q3_K_L.gguf new file mode 100644 index 0000000..599c4e0 --- /dev/null +++ b/L3.1-Athena-b-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31122333640fc8c558bf10714f342c2cd3a06a40e34b2054bd67188fbb5fe335 +size 4321964096 diff --git a/L3.1-Athena-b-8B.Q3_K_M.gguf b/L3.1-Athena-b-8B.Q3_K_M.gguf new file mode 100644 index 0000000..1f784f9 --- /dev/null +++ b/L3.1-Athena-b-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f070087029daf870e383f405fb54b5ac15db1b693fba749cdec112015e07af1c +size 4018925632 diff --git a/L3.1-Athena-b-8B.Q3_K_S.gguf b/L3.1-Athena-b-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5de54d9 --- /dev/null +++ b/L3.1-Athena-b-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4622fb8f32a65309da28f31068206d3fb9ed954e78f9d3430af5dec7c623cefa +size 3664506944 diff --git a/L3.1-Athena-b-8B.Q4_K_M.gguf b/L3.1-Athena-b-8B.Q4_K_M.gguf new file mode 100644 index 0000000..308828e --- /dev/null +++ b/L3.1-Athena-b-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9c7247032ba2bce444b5ae9d06ffeb0f0008a0c3e19d5b9edd2907d6c7b305 +size 4920741952 diff --git a/L3.1-Athena-b-8B.Q4_K_S.gguf b/L3.1-Athena-b-8B.Q4_K_S.gguf new file mode 100644 index 0000000..b02bad9 --- /dev/null +++ b/L3.1-Athena-b-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ddcd2db3303b6615f7d923011caf47450d58b0894611ecfcbc175cb6a483bc +size 4692676672 diff --git a/L3.1-Athena-b-8B.Q5_K_M.gguf b/L3.1-Athena-b-8B.Q5_K_M.gguf new file mode 100644 index 0000000..974915f --- /dev/null +++ b/L3.1-Athena-b-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e991dfc2efb926df02e08bd703c3fc629d071c7103ba7c510639d4658f4e3f +size 5732995136 diff --git a/L3.1-Athena-b-8B.Q5_K_S.gguf b/L3.1-Athena-b-8B.Q5_K_S.gguf new file mode 100644 index 0000000..38f8d98 --- /dev/null +++ b/L3.1-Athena-b-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da6fd23e7b962289b197fe311a36df17946967a537d9a718c4ec7ee09f1ea99 +size 5599301696 diff --git a/L3.1-Athena-b-8B.Q6_K.gguf b/L3.1-Athena-b-8B.Q6_K.gguf new file mode 100644 index 0000000..1a40ec3 --- /dev/null +++ b/L3.1-Athena-b-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5b74d24df841f2c1eddaa91a40183a3eb2461f7450741ad144e3a3d9ab3faa +size 6596014144 diff --git a/L3.1-Athena-b-8B.Q8_0.gguf b/L3.1-Athena-b-8B.Q8_0.gguf new file mode 100644 index 0000000..4bc2d14 --- /dev/null +++ b/L3.1-Athena-b-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c364669529133463f31936051cc05c9821df513cd07c32057e179c3f8f7bc5ac +size 8540778560 diff --git a/L3.1-Athena-b-8B.f16.gguf b/L3.1-Athena-b-8B.f16.gguf new file mode 100644 index 0000000..7b7c669 --- /dev/null +++ b/L3.1-Athena-b-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ebb5dd9d6c9ea03b670f34d874002a90c914bc4148487f60a8a87034665e98 +size 16068898880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93e2a36 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mergekit-community/L3.1-Athena-b-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/L3.1-Athena-b-8B + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-b-8B-GGUF/resolve/main/L3.1-Athena-b-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. + +