commit 94052ee47e7a84d68c969a9d5254deb3f7c3f177 Author: ModelHub XC Date: Mon Nov 2 15:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hercules-Mini-1.8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e17434 --- /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 +Hercules-Mini-1.8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Mini-1.8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hercules-Mini-1.8B.IQ4_XS.gguf b/Hercules-Mini-1.8B.IQ4_XS.gguf new file mode 100644 index 0000000..d5b044b --- /dev/null +++ b/Hercules-Mini-1.8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098d25aef43bf6dcc525c24089afa6d98d7fd9c0c1ce13cf9a9c960143f07fad +size 1087361856 diff --git a/Hercules-Mini-1.8B.Q2_K.gguf b/Hercules-Mini-1.8B.Q2_K.gguf new file mode 100644 index 0000000..cb216f2 --- /dev/null +++ b/Hercules-Mini-1.8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac4ad3810f6597ad7e70648c70d1825f0c2fa5745abc6fbc67ad3332be5226b +size 846570304 diff --git a/Hercules-Mini-1.8B.Q3_K_L.gguf b/Hercules-Mini-1.8B.Q3_K_L.gguf new file mode 100644 index 0000000..a3fb539 --- /dev/null +++ b/Hercules-Mini-1.8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7c519d4427f58d4540c75de3fa156fc2b92702e54600ed0b3c7d609efa5a3a +size 1056201536 diff --git a/Hercules-Mini-1.8B.Q3_K_M.gguf b/Hercules-Mini-1.8B.Q3_K_M.gguf new file mode 100644 index 0000000..6617c61 --- /dev/null +++ b/Hercules-Mini-1.8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2404ba0a34569cd60a674a0ba9be1064de2565ad435fdfbe00615de60be0c2 +size 1015880512 diff --git a/Hercules-Mini-1.8B.Q3_K_S.gguf b/Hercules-Mini-1.8B.Q3_K_S.gguf new file mode 100644 index 0000000..7e43872 --- /dev/null +++ b/Hercules-Mini-1.8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a8e43c1d5cd59b23c0e814672f427e2f8b2eb22edc20ff707b83b0dff66c7e +size 953572160 diff --git a/Hercules-Mini-1.8B.Q4_K_M.gguf b/Hercules-Mini-1.8B.Q4_K_M.gguf new file mode 100644 index 0000000..5d059a4 --- /dev/null +++ b/Hercules-Mini-1.8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6fb440e060a46fec1b202c2709bfa5bba11471f411d1eb9088d23c3d19cf76 +size 1217753920 diff --git a/Hercules-Mini-1.8B.Q4_K_S.gguf b/Hercules-Mini-1.8B.Q4_K_S.gguf new file mode 100644 index 0000000..28194af --- /dev/null +++ b/Hercules-Mini-1.8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cbbbf6bc52f5d96540123a81082402dd58d71081f266a7c4049064b1bbbff55 +size 1158263616 diff --git a/Hercules-Mini-1.8B.Q5_K_M.gguf b/Hercules-Mini-1.8B.Q5_K_M.gguf new file mode 100644 index 0000000..8c47470 --- /dev/null +++ b/Hercules-Mini-1.8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3dd95c4afb31581baa61d21393b59678059543128a116c7f8fcadfdff565b9 +size 1376777024 diff --git a/Hercules-Mini-1.8B.Q5_K_S.gguf b/Hercules-Mini-1.8B.Q5_K_S.gguf new file mode 100644 index 0000000..391974f --- /dev/null +++ b/Hercules-Mini-1.8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:852368507bd1d7b2ac0c24b53ae4dba9158aaf6b34b64d4ee0d5ea17f64db257 +size 1327821632 diff --git a/Hercules-Mini-1.8B.Q6_K.gguf b/Hercules-Mini-1.8B.Q6_K.gguf new file mode 100644 index 0000000..22dcd7d --- /dev/null +++ b/Hercules-Mini-1.8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd12991bb72e0651683e32c729d25baf375a7bad67a593ab1985caca169feeb5 +size 1579027264 diff --git a/Hercules-Mini-1.8B.Q8_0.gguf b/Hercules-Mini-1.8B.Q8_0.gguf new file mode 100644 index 0000000..e91815a --- /dev/null +++ b/Hercules-Mini-1.8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395156e67755eb1fd24d1777b92fa2242116525a7affa97914160416cf41e170 +size 1958304576 diff --git a/Hercules-Mini-1.8B.f16.gguf b/Hercules-Mini-1.8B.f16.gguf new file mode 100644 index 0000000..e56d236 --- /dev/null +++ b/Hercules-Mini-1.8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc98a316507c4cbfa9edb3cbb6509128d08b213f4853c74e8c1fde6cdad1dec +size 3680099136 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7c1f35 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: M4-ai/Hercules-Mini-1.8B +datasets: +- Locutusque/hercules-v4.0 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/M4-ai/Hercules-Mini-1.8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hercules-Mini-1.8B-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/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Mini-1.8B-GGUF/resolve/main/Hercules-Mini-1.8B.f16.gguf) | f16 | 3.8 | 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. + +