commit 902f616ded8ffd49baf3f9512398fd4654f9af97 Author: ModelHub XC Date: Tue Sep 1 11:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40c18c7 --- /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 +Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Opus-Z8-Heretic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.IQ4_XS.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.IQ4_XS.gguf new file mode 100644 index 0000000..a3fbc88 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935e659230f23b07795ae8917e01e361c1640bf32ad86c39cd0dbd8a96517f12 +size 4484367552 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q2_K.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q2_K.gguf new file mode 100644 index 0000000..9ba367f --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a422e2a7923c0e450f16e460dbe1262a2e68503a2d69c60262e1d198be62df4 +size 3179136192 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_L.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_L.gguf new file mode 100644 index 0000000..d5caca8 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850cf7b0dedfec8a637fce216a1c3a86f59763e5880c27094841e49a075c0c3d +size 4321961152 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_M.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_M.gguf new file mode 100644 index 0000000..9ef14a2 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4adeecfe8b8d5fba8eb109eabdc45ba1b0107b47274961a581777613a98e6913 +size 4018922688 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_S.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_S.gguf new file mode 100644 index 0000000..af53e10 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747ae50105a6728e381d9b256d6ad24879f3a45426edad4840c160de388c1231 +size 3664504000 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_M.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_M.gguf new file mode 100644 index 0000000..d64dd46 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf7fd09be99546b6ed96e72f62d15ce9f74ff38dec29081c14e740461a1a9b4 +size 4920739008 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_S.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_S.gguf new file mode 100644 index 0000000..b157513 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a31e9809b6802f88f389472cbf50a3e5b6df75b8a10c784a3fd6bdc92749c8c +size 4692673728 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_M.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_M.gguf new file mode 100644 index 0000000..f05f27e --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f80638eaa76a83f336ddee88b4534048d9fa0e408a54de75ac4bab7b0a2bf01 +size 5732992192 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_S.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_S.gguf new file mode 100644 index 0000000..9801c5d --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26bbf4aa0ad30574cf8da20beab2f18d74d523411ff42a669aaec80c610bb6c3 +size 5599298752 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q6_K.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q6_K.gguf new file mode 100644 index 0000000..3463eaf --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd35090b4b32e3931d6cafb70e65d81553c93711f9d345ba851aefcb08101c3d +size 6596011200 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.Q8_0.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.Q8_0.gguf new file mode 100644 index 0000000..b23a1d8 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048843ca9549c7490b1fe85ff453c38cbe2b7b9aa95621d053279d0f68440dae +size 8540775616 diff --git a/Llama-3.3-8B-Opus-Z8-Heretic.f16.gguf b/Llama-3.3-8B-Opus-Z8-Heretic.f16.gguf new file mode 100644 index 0000000..a669372 --- /dev/null +++ b/Llama-3.3-8B-Opus-Z8-Heretic.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735210a1443947e0b4d564c86fae6f76e125e85fc7cbb93b9a307df336c66cd2 +size 16068895936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..785f521 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: ChiKoi7/Llama-3.3-8B-Opus-Z8-Heretic +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- Uncensored +- Heretic +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ChiKoi7/Llama-3.3-8B-Opus-Z8-Heretic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Opus-Z8-Heretic-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-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-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Opus-Z8-Heretic-GGUF/resolve/main/Llama-3.3-8B-Opus-Z8-Heretic.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. + +