commit 530292c1b3a08967dd42a88839e5399dd8896050 Author: ModelHub XC Date: Sun Oct 4 16:19:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MetaAPO-Llama3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f4f53a9 --- /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 +MetaAPO-Llama3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MetaAPO-Llama3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MetaAPO-Llama3.1-8B.IQ4_XS.gguf b/MetaAPO-Llama3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..c164852 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28944b47c88e4b8527bf604e54349759e599596d22cc393764919f5ce1f381e9 +size 4484408224 diff --git a/MetaAPO-Llama3.1-8B.Q2_K.gguf b/MetaAPO-Llama3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..c7fb03b --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c436f20d7a3d820763ec8e4939a2cd44b30ced97bb8fd683d8a8ae5a5dfe207b +size 3179170208 diff --git a/MetaAPO-Llama3.1-8B.Q3_K_L.gguf b/MetaAPO-Llama3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..16cd505 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fb70d956083a369c670440b1bacd6f2e38a3a82366b6bf96438f4b52db7275 +size 4321998496 diff --git a/MetaAPO-Llama3.1-8B.Q3_K_M.gguf b/MetaAPO-Llama3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..6b94e07 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff53756670d851829f635a20c11d14d24b111ac62ab29e353530ae9a1d6e4a80 +size 4018960032 diff --git a/MetaAPO-Llama3.1-8B.Q3_K_S.gguf b/MetaAPO-Llama3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..4f23d91 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6cce86b6c8980a8b93725d684c8d8409811bbe9e4253f31052a8835e252571 +size 3664541344 diff --git a/MetaAPO-Llama3.1-8B.Q4_K_M.gguf b/MetaAPO-Llama3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..41b52e9 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a572870d51bce53fc95aee0da40327d6ddbb273efae11aa207cc4ab0171c480a +size 4920780704 diff --git a/MetaAPO-Llama3.1-8B.Q4_K_S.gguf b/MetaAPO-Llama3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..d9bb7c6 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f574afeabbf4b4c5e09c264d9c07ccc781248eac6f9ac95194997d6ced5460 +size 4692715424 diff --git a/MetaAPO-Llama3.1-8B.Q5_K_M.gguf b/MetaAPO-Llama3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..980c94e --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0faabf96bdbd71aa402d352a66c5e38e9c31a6fd317d53eefd2378355c945b +size 5733037984 diff --git a/MetaAPO-Llama3.1-8B.Q5_K_S.gguf b/MetaAPO-Llama3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..821c8a3 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1273babfb885ab4fde566c5022f0c373a8d4cf9f00703d13a5333eb1f845f815 +size 5599344544 diff --git a/MetaAPO-Llama3.1-8B.Q6_K.gguf b/MetaAPO-Llama3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..0de5689 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527aa5b4bdcbf1e592b9cd1a842f711e2164f8b57a6a1af0686c69e33081847f +size 6596061344 diff --git a/MetaAPO-Llama3.1-8B.Q8_0.gguf b/MetaAPO-Llama3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..bd12218 --- /dev/null +++ b/MetaAPO-Llama3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db45dda596d9ea444e0aa43fa532697951b8672aa5ac6bbfc61929551d00224 +size 8540841632 diff --git a/MetaAPO-Llama3.1-8B.f16.gguf b/MetaAPO-Llama3.1-8B.f16.gguf new file mode 100644 index 0000000..2ab5aba --- /dev/null +++ b/MetaAPO-Llama3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc921d06899fcc4e1d2d6df3d38c5fbe7620669287c27f3feac934f85302c772 +size 16069023392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc210b7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: jmyang/MetaAPO-Llama3.1-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jmyang/MetaAPO-Llama3.1-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MetaAPO-Llama3.1-8B-GGUF).*** + +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/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MetaAPO-Llama3.1-8B-GGUF/resolve/main/MetaAPO-Llama3.1-8B.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. + +