commit fcf3143b3438d83fb0128a2e1a7e0ec50bd0e892 Author: ModelHub XC Date: Tue Apr 21 10:42:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Heretic-Llama-Express.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4ef801d --- /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 +Heretic-Llama-Express.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Heretic-Llama-Express.1.IQ4_XS.gguf b/Heretic-Llama-Express.1.IQ4_XS.gguf new file mode 100644 index 0000000..63f7ec1 --- /dev/null +++ b/Heretic-Llama-Express.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7672ac54da4d51ebad4061ee3ab753bcab246cddcab98571a730548fe0b52d97 +size 748385472 diff --git a/Heretic-Llama-Express.1.Q2_K.gguf b/Heretic-Llama-Express.1.Q2_K.gguf new file mode 100644 index 0000000..c94ec47 --- /dev/null +++ b/Heretic-Llama-Express.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef9c250154c3deb4ab1b1cffa21e337af3adb28fdc2c7a5d8665c2096f26e80 +size 580875456 diff --git a/Heretic-Llama-Express.1.Q3_K_L.gguf b/Heretic-Llama-Express.1.Q3_K_L.gguf new file mode 100644 index 0000000..a6833e3 --- /dev/null +++ b/Heretic-Llama-Express.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11cf4223371fb6e3d11b55511b8af91396ba17e7ff9c6ec5130b620291a4a04 +size 732525760 diff --git a/Heretic-Llama-Express.1.Q3_K_M.gguf b/Heretic-Llama-Express.1.Q3_K_M.gguf new file mode 100644 index 0000000..cc506f3 --- /dev/null +++ b/Heretic-Llama-Express.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668526bbaf831e5eb9afd7be1f2de81b239b6c17a7ee1dd0df5fc543d03e7431 +size 690844864 diff --git a/Heretic-Llama-Express.1.Q3_K_S.gguf b/Heretic-Llama-Express.1.Q3_K_S.gguf new file mode 100644 index 0000000..b44bcf2 --- /dev/null +++ b/Heretic-Llama-Express.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b696f765f6d9c05dc964c9d2128545fe559e5c3c00aa1ba65c7ed40b1eee6c +size 641692864 diff --git a/Heretic-Llama-Express.1.Q4_K_M.gguf b/Heretic-Llama-Express.1.Q4_K_M.gguf new file mode 100644 index 0000000..4be2fed --- /dev/null +++ b/Heretic-Llama-Express.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44861cb403404ed2521723158cb673bb63004d6571265439e05891f5a58118e9 +size 807695552 diff --git a/Heretic-Llama-Express.1.Q4_K_S.gguf b/Heretic-Llama-Express.1.Q4_K_S.gguf new file mode 100644 index 0000000..9635f4f --- /dev/null +++ b/Heretic-Llama-Express.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41662b17cc799806e153798489642a0d54e7d02e658f509ee0ae15a2c8beab44 +size 775648448 diff --git a/Heretic-Llama-Express.1.Q5_K_M.gguf b/Heretic-Llama-Express.1.Q5_K_M.gguf new file mode 100644 index 0000000..7f9f52b --- /dev/null +++ b/Heretic-Llama-Express.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cba4bcb0b1bb4d1959c6d069957ab951694e26fe898a718312f7bd5ee59d308 +size 911504576 diff --git a/Heretic-Llama-Express.1.Q5_K_S.gguf b/Heretic-Llama-Express.1.Q5_K_S.gguf new file mode 100644 index 0000000..5da3731 --- /dev/null +++ b/Heretic-Llama-Express.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89a1cdb479bcdaab29d1f463b14b97fa55d378049055b98f74ee9208ffc9990 +size 892564672 diff --git a/Heretic-Llama-Express.1.Q6_K.gguf b/Heretic-Llama-Express.1.Q6_K.gguf new file mode 100644 index 0000000..a6a39b8 --- /dev/null +++ b/Heretic-Llama-Express.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2a454c4792af42177d9f4f2e160f1e8b500eaf3d64bfd89b26242335d00f24 +size 1021801664 diff --git a/Heretic-Llama-Express.1.Q8_0.gguf b/Heretic-Llama-Express.1.Q8_0.gguf new file mode 100644 index 0000000..3d17f3d --- /dev/null +++ b/Heretic-Llama-Express.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4caeac676ba2e98e72117453f1b0a48210d5e299d5a12888eeb920e1ef17cfbf +size 1321084096 diff --git a/Heretic-Llama-Express.1.f16.gguf b/Heretic-Llama-Express.1.f16.gguf new file mode 100644 index 0000000..83111d9 --- /dev/null +++ b/Heretic-Llama-Express.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0161ecde85a5fb8e8e466768b213d5cfcb7a5cbd55b23eeb3014dfb4141f06da +size 2479596736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9108762 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: hereticness/Heretic-Llama-Express.1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hereticness/Heretic-Llama-Express.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Heretic-Llama-Express.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Heretic-Llama-Express.1-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/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-GGUF/resolve/main/Heretic-Llama-Express.1.f16.gguf) | f16 | 2.6 | 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. + +