commit 03c02f0460e6fcf184a37d78623f063357253e5c Author: ModelHub XC Date: Sun Jul 19 08:19:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Hercules-5.0-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f8347a3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-Hercules-5.0-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Hercules-5.0-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Hercules-5.0-8B.IQ3_M.gguf b/Llama-3-Hercules-5.0-8B.IQ3_M.gguf new file mode 100644 index 0000000..eeb70b3 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb451c755bd6975bcf2082c8183dd74d2c5b0dbb61a6a47c9ba82e6772ada5b +size 3784823136 diff --git a/Llama-3-Hercules-5.0-8B.IQ3_S.gguf b/Llama-3-Hercules-5.0-8B.IQ3_S.gguf new file mode 100644 index 0000000..fb61cc3 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ea078e54377f9083e49cba77c062a17f997aae44271cacdd8691040c728fe0 +size 3682324832 diff --git a/Llama-3-Hercules-5.0-8B.IQ3_XS.gguf b/Llama-3-Hercules-5.0-8B.IQ3_XS.gguf new file mode 100644 index 0000000..4e0c14d --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043dc0edef8129d9c1967df6d0f8980da9502b2a5a2df2c25dad6f18ab3fd835 +size 3518746976 diff --git a/Llama-3-Hercules-5.0-8B.IQ4_XS.gguf b/Llama-3-Hercules-5.0-8B.IQ4_XS.gguf new file mode 100644 index 0000000..adf12eb --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0893cfc22e3d2dfaa754d58f5507ba54bea82c0e4cd4db2701a47da3673c6fb8 +size 4484362592 diff --git a/Llama-3-Hercules-5.0-8B.Q2_K.gguf b/Llama-3-Hercules-5.0-8B.Q2_K.gguf new file mode 100644 index 0000000..480cacf --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9156e869fc0bdedde3ed85f53389b52b530508bf08294264ed316db649fcd6 +size 3179131232 diff --git a/Llama-3-Hercules-5.0-8B.Q3_K_L.gguf b/Llama-3-Hercules-5.0-8B.Q3_K_L.gguf new file mode 100644 index 0000000..1823ccd --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194b9f2aa96d89acc0819b20ac8d23c8847f258cd1221d7abab02f4ef750d77f +size 4321956192 diff --git a/Llama-3-Hercules-5.0-8B.Q3_K_M.gguf b/Llama-3-Hercules-5.0-8B.Q3_K_M.gguf new file mode 100644 index 0000000..36d2d11 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09644fca00d2545dacb8792ab917d6341189cabafb3a6a191b8f7b91596ebcfb +size 4018917728 diff --git a/Llama-3-Hercules-5.0-8B.Q3_K_S.gguf b/Llama-3-Hercules-5.0-8B.Q3_K_S.gguf new file mode 100644 index 0000000..6ec5980 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e457cc79e52f5adcae6db4e6a83012d957ba59f3441676bcfef401cd91e39c39 +size 3664499040 diff --git a/Llama-3-Hercules-5.0-8B.Q4_K_M.gguf b/Llama-3-Hercules-5.0-8B.Q4_K_M.gguf new file mode 100644 index 0000000..2842e8f --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac883f01ffb2ab2d49c8e9efaf3843cf86cbf599fd99e4ccf9475b96c0110724 +size 4920734048 diff --git a/Llama-3-Hercules-5.0-8B.Q4_K_S.gguf b/Llama-3-Hercules-5.0-8B.Q4_K_S.gguf new file mode 100644 index 0000000..c277b89 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7582ea4dfc4d5dfaa7bddea40cd0c466978b8b361ab79dc6373a8baccf8e424 +size 4692668768 diff --git a/Llama-3-Hercules-5.0-8B.Q5_K_M.gguf b/Llama-3-Hercules-5.0-8B.Q5_K_M.gguf new file mode 100644 index 0000000..9b7f76e --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe13ab1151deeedb3c5e135d09631aec4010ed76c3753a6bdc5470278ad9dd1 +size 5732987232 diff --git a/Llama-3-Hercules-5.0-8B.Q5_K_S.gguf b/Llama-3-Hercules-5.0-8B.Q5_K_S.gguf new file mode 100644 index 0000000..94f7b2f --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbc473dff5e2ae0922a5b00cfc70e947d99f0ca80972a59f1302ec03cc79a4a3 +size 5599293792 diff --git a/Llama-3-Hercules-5.0-8B.Q6_K.gguf b/Llama-3-Hercules-5.0-8B.Q6_K.gguf new file mode 100644 index 0000000..9206904 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4f4fea2a99b24f8b86c177fb419164860a310d0f77d75b776e0368915bcff7 +size 6596006240 diff --git a/Llama-3-Hercules-5.0-8B.Q8_0.gguf b/Llama-3-Hercules-5.0-8B.Q8_0.gguf new file mode 100644 index 0000000..5f4a6e6 --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacd10285e7711c96a5c5be40c35875260a4c55ab35bfc3d19709935384df6fe +size 8540770656 diff --git a/Llama-3-Hercules-5.0-8B.f16.gguf b/Llama-3-Hercules-5.0-8B.f16.gguf new file mode 100644 index 0000000..046e2fd --- /dev/null +++ b/Llama-3-Hercules-5.0-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f752428b9692edc32b56b3504df6016246dbcc6578a2bc65268300f635b2b2 +size 16068890976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a4a8983 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Locutusque/Llama-3-Hercules-5.0-8B +datasets: +- Locutusque/hercules-v5.0 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Locutusque/Llama-3-Hercules-5.0-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-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/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Hercules-5.0-8B-GGUF/resolve/main/Llama-3-Hercules-5.0-8B.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. + +