commit 22d6703a3ed26482884b9fdaa8f370e99c5c9b15 Author: ModelHub XC Date: Thu Jun 11 11:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Athena-e-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2301d18 --- /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-e-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Athena-e-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Athena-e-8B.IQ4_XS.gguf b/L3.1-Athena-e-8B.IQ4_XS.gguf new file mode 100644 index 0000000..e5414c5 --- /dev/null +++ b/L3.1-Athena-e-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7558d754ceb2123e0bdbf73f532b304cba7b5dfadda522936969a5f8ab1eeb7 +size 4484371392 diff --git a/L3.1-Athena-e-8B.Q2_K.gguf b/L3.1-Athena-e-8B.Q2_K.gguf new file mode 100644 index 0000000..3dd8f09 --- /dev/null +++ b/L3.1-Athena-e-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa307a2594ad1fb71325f62447aaf3e86d36750dee22e96767754a52c8cbb913 +size 3179140032 diff --git a/L3.1-Athena-e-8B.Q3_K_L.gguf b/L3.1-Athena-e-8B.Q3_K_L.gguf new file mode 100644 index 0000000..b25fd9f --- /dev/null +++ b/L3.1-Athena-e-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f48144865c5d1f3cc942c6d2acd7ed5ddbd0eb7e680d0e96a71e3336dea4263 +size 4321964992 diff --git a/L3.1-Athena-e-8B.Q3_K_M.gguf b/L3.1-Athena-e-8B.Q3_K_M.gguf new file mode 100644 index 0000000..dcb8aa4 --- /dev/null +++ b/L3.1-Athena-e-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9127db232758fb3d98628df2ef7d8b712d21de4a712626a15e68edf4058069 +size 4018926528 diff --git a/L3.1-Athena-e-8B.Q3_K_S.gguf b/L3.1-Athena-e-8B.Q3_K_S.gguf new file mode 100644 index 0000000..24196d0 --- /dev/null +++ b/L3.1-Athena-e-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69447ea3379fb12e01388b44f84b2fa188c24f1f89e7081183a1cd98f604b4b1 +size 3664507840 diff --git a/L3.1-Athena-e-8B.Q4_K_M.gguf b/L3.1-Athena-e-8B.Q4_K_M.gguf new file mode 100644 index 0000000..955b40f --- /dev/null +++ b/L3.1-Athena-e-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d003209e3cca1f79472b1cb0494dd9b18d4293a30f42371e0a3c131193056c +size 4920742848 diff --git a/L3.1-Athena-e-8B.Q4_K_S.gguf b/L3.1-Athena-e-8B.Q4_K_S.gguf new file mode 100644 index 0000000..7830bd2 --- /dev/null +++ b/L3.1-Athena-e-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e88e6839e56777f91d8810408e67cdeb6983cbfeab1c1b6e3d0cffd17c2982e +size 4692677568 diff --git a/L3.1-Athena-e-8B.Q5_K_M.gguf b/L3.1-Athena-e-8B.Q5_K_M.gguf new file mode 100644 index 0000000..b7b124b --- /dev/null +++ b/L3.1-Athena-e-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36a7800caf40e18ae7e6a30d557a100c91a2d4f592b27322d6863d6bc8912cf4 +size 5732996032 diff --git a/L3.1-Athena-e-8B.Q5_K_S.gguf b/L3.1-Athena-e-8B.Q5_K_S.gguf new file mode 100644 index 0000000..e81a0f0 --- /dev/null +++ b/L3.1-Athena-e-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ed6dcb7172d684f2ffc3ecc09bd7fcc5932fbc1b23a9281d2b09c7ede6f00c +size 5599302592 diff --git a/L3.1-Athena-e-8B.Q6_K.gguf b/L3.1-Athena-e-8B.Q6_K.gguf new file mode 100644 index 0000000..3c3169b --- /dev/null +++ b/L3.1-Athena-e-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42737fe6fc6c26e60b0c482d2a7cf857e087f14ceadb4552c3d16535ac8ef62e +size 6596015040 diff --git a/L3.1-Athena-e-8B.Q8_0.gguf b/L3.1-Athena-e-8B.Q8_0.gguf new file mode 100644 index 0000000..589d246 --- /dev/null +++ b/L3.1-Athena-e-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd4611da8882add902569705db24bd39bdde64f1bcc5523710aa02dcccb6a05 +size 8540779456 diff --git a/L3.1-Athena-e-8B.f16.gguf b/L3.1-Athena-e-8B.f16.gguf new file mode 100644 index 0000000..f84f32c --- /dev/null +++ b/L3.1-Athena-e-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6a8814a752276f3e976cfc01aa30efb315c4fccfc38380537a58c962dccb7e +size 16068899776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a5e4591 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mergekit-community/L3.1-Athena-e-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/L3.1-Athena-e-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-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Athena-e-8B-GGUF/resolve/main/L3.1-Athena-e-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. + +