commit b6273502f7fe33ab281f451f451e4096254c22d4 Author: ModelHub XC Date: Wed Apr 22 04:56:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b683252 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama-3.1-8B-Instruct-Zeus.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Zeus.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Instruct-Zeus.IQ4_XS.gguf b/Llama-3.1-8B-Instruct-Zeus.IQ4_XS.gguf new file mode 100644 index 0000000..8eff278 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff89737c47157570b83bf9c311a561bdbc2b1e91fee3ca4aa2a40f14029c7287 +size 4484368960 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q2_K.gguf b/Llama-3.1-8B-Instruct-Zeus.Q2_K.gguf new file mode 100644 index 0000000..54584fe --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7ff6c2ab85eaa4292a303da82e458ca329f2bfcd1d37049c4b4b0f3137c2a4 +size 3179137600 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q3_K_L.gguf b/Llama-3.1-8B-Instruct-Zeus.Q3_K_L.gguf new file mode 100644 index 0000000..9ee76f6 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a13d55e86205fb2ce565f68b530a5b9bcaa1eb4fa89435efdae42f7e1483ad +size 4321962560 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q3_K_M.gguf b/Llama-3.1-8B-Instruct-Zeus.Q3_K_M.gguf new file mode 100644 index 0000000..9e3be3b --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65472eab991c7747e576daef54c099d3cd2b176c6d2aa15b1531c3c015d2772 +size 4018924096 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q3_K_S.gguf b/Llama-3.1-8B-Instruct-Zeus.Q3_K_S.gguf new file mode 100644 index 0000000..f3110e7 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9e3fec2299d58ee7bdaf7527c21e28be76d88b60ff82e3a69c08cd8b4254bc +size 3664505408 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q4_0_4_4.gguf b/Llama-3.1-8B-Instruct-Zeus.Q4_0_4_4.gguf new file mode 100644 index 0000000..3dd2a21 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6a96b5b6249315362703464d4509e9621751376c62dfc4721cdd928d211af6 +size 4661217856 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q4_K_M.gguf b/Llama-3.1-8B-Instruct-Zeus.Q4_K_M.gguf new file mode 100644 index 0000000..3c614fb --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445cdab3f0cbdf2aa4d8c9c8f1286a98d3d04da67d45dd0bd23149dd52c156a2 +size 4920740416 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q4_K_S.gguf b/Llama-3.1-8B-Instruct-Zeus.Q4_K_S.gguf new file mode 100644 index 0000000..c83f3dd --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd7b68779a52a7b441f7bc80b7eb7f0d03b48197f25d94a1f1d087a3f41dda2a +size 4692675136 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q5_K_M.gguf b/Llama-3.1-8B-Instruct-Zeus.Q5_K_M.gguf new file mode 100644 index 0000000..fc9e9ce --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5ad1df8f81425394befdfbd76652c8cd81f32ac41d79177dd69ae929390873 +size 5732993600 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q5_K_S.gguf b/Llama-3.1-8B-Instruct-Zeus.Q5_K_S.gguf new file mode 100644 index 0000000..c22addd --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715ffe0c389d6661e1e99ffc1efa9ece3de65efac4988d11547ae87bbaf1e85e +size 5599300160 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q6_K.gguf b/Llama-3.1-8B-Instruct-Zeus.Q6_K.gguf new file mode 100644 index 0000000..bf92386 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f476277801dbb6fa202051ec6b3aede6bbc8f0b699a58ff2ea41294742264c +size 6596012608 diff --git a/Llama-3.1-8B-Instruct-Zeus.Q8_0.gguf b/Llama-3.1-8B-Instruct-Zeus.Q8_0.gguf new file mode 100644 index 0000000..118884b --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de426f0306e93daee141c6c5dcc9958aea9525f04f894be7e10d0463428faf1b +size 8540777024 diff --git a/Llama-3.1-8B-Instruct-Zeus.f16.gguf b/Llama-3.1-8B-Instruct-Zeus.f16.gguf new file mode 100644 index 0000000..26073cb --- /dev/null +++ b/Llama-3.1-8B-Instruct-Zeus.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492decffd975fbc537da1875097234ea5acf67ae0ebd0efb95f787cddbfb2db6 +size 16068897344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4e518d3 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: T145/Llama-3.1-8B-Instruct-Zeus +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +- llama-3.1 +- roleplay +- function calling +--- +## About + + + + + + +static quants of https://huggingface.co/T145/Llama-3.1-8B-Instruct-Zeus + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-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/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Zeus-GGUF/resolve/main/Llama-3.1-8B-Instruct-Zeus.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. 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. + +