commit 48fb638157dc67ec8b143d9721b7bb160b8cb8b6 Author: ModelHub XC Date: Thu Jun 18 00:58:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4cf6f66 --- /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-Instruct-heretic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-heretic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Instruct-heretic.IQ4_XS.gguf b/Llama-3.3-8B-Instruct-heretic.IQ4_XS.gguf new file mode 100644 index 0000000..67cfbfd --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc67263f8eebbbbdce0284d4faa4dfb41afb430fdb87dcae8dcf5f26d8d94af7 +size 4484363552 diff --git a/Llama-3.3-8B-Instruct-heretic.Q2_K.gguf b/Llama-3.3-8B-Instruct-heretic.Q2_K.gguf new file mode 100644 index 0000000..9a041f6 --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ef3ef41408dee3de77f53ecff06d612f6bfcaf11658137986fb6c03e4f88d1 +size 3179132192 diff --git a/Llama-3.3-8B-Instruct-heretic.Q3_K_L.gguf b/Llama-3.3-8B-Instruct-heretic.Q3_K_L.gguf new file mode 100644 index 0000000..64df34f --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bb659c3765906c71425da062d2108c3b464a0efc01a697c7507c5b3f08d55c +size 4321957152 diff --git a/Llama-3.3-8B-Instruct-heretic.Q3_K_M.gguf b/Llama-3.3-8B-Instruct-heretic.Q3_K_M.gguf new file mode 100644 index 0000000..10c39d8 --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756489999ac20323705dd28a3f89b096d3a0287eb5a10e126528ff42d94e9388 +size 4018918688 diff --git a/Llama-3.3-8B-Instruct-heretic.Q3_K_S.gguf b/Llama-3.3-8B-Instruct-heretic.Q3_K_S.gguf new file mode 100644 index 0000000..3196724 --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c529be16acbc5dc54d4ecffbb6e8d8259dc55bda8f0ed86fb9c9046f1f312619 +size 3664500000 diff --git a/Llama-3.3-8B-Instruct-heretic.Q4_K_M.gguf b/Llama-3.3-8B-Instruct-heretic.Q4_K_M.gguf new file mode 100644 index 0000000..e42f106 --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b87e19a38d575530afd2518aacca844ecba2ae08cf58fb4d8762b7c667d1a4 +size 4920735008 diff --git a/Llama-3.3-8B-Instruct-heretic.Q4_K_S.gguf b/Llama-3.3-8B-Instruct-heretic.Q4_K_S.gguf new file mode 100644 index 0000000..2dccf7b --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab24cc4b6d525a15a7f079fc6522acacbe146a37e5bf8996ef089556c26b18b5 +size 4692669728 diff --git a/Llama-3.3-8B-Instruct-heretic.Q5_K_M.gguf b/Llama-3.3-8B-Instruct-heretic.Q5_K_M.gguf new file mode 100644 index 0000000..660d15b --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad0ebbfa90624e1a5f76ab9f6ab5bf0eeb6f3590848c233e53d1a76c1b250c4 +size 5732988192 diff --git a/Llama-3.3-8B-Instruct-heretic.Q5_K_S.gguf b/Llama-3.3-8B-Instruct-heretic.Q5_K_S.gguf new file mode 100644 index 0000000..1a11e4b --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f3b413e738c18556277c665de8b0e1c8e797c691eb82d055bccfabf03d7866 +size 5599294752 diff --git a/Llama-3.3-8B-Instruct-heretic.Q6_K.gguf b/Llama-3.3-8B-Instruct-heretic.Q6_K.gguf new file mode 100644 index 0000000..d1864bf --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7123d220849f002704f168782af71ea6a1ce48295795e68a9444304405e9f08 +size 6596007200 diff --git a/Llama-3.3-8B-Instruct-heretic.Q8_0.gguf b/Llama-3.3-8B-Instruct-heretic.Q8_0.gguf new file mode 100644 index 0000000..3e71fb1 --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6431fe6144836a342d10ab9a82133bbcfd5805785ef00a3e7163f60f59aa513c +size 8540771616 diff --git a/Llama-3.3-8B-Instruct-heretic.f16.gguf b/Llama-3.3-8B-Instruct-heretic.f16.gguf new file mode 100644 index 0000000..308848a --- /dev/null +++ b/Llama-3.3-8B-Instruct-heretic.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3bf4f047085e3157e7ada838a33a926d0fc41230923111b41c300e7e014a214 +size 16068891936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a9f40b6 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: aeon37/Llama-3.3-8B-Instruct-heretic +language: +- en +library_name: transformers +license: llama3.3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +- uncensored +- decensored +- abliterated +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aeon37/Llama-3.3-8B-Instruct-heretic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Instruct-heretic-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-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-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-heretic.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-heretic-GGUF/resolve/main/Llama-3.3-8B-Instruct-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. + +