commit 64808b5d9c67e09d7cab417dc7877a3dd4a0d11c Author: ModelHub XC Date: Fri Jul 24 02:51:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Unholy-8B-e4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0323397 --- /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-Unholy-8B-e4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Unholy-8B-e4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Unholy-8B-e4.IQ4_XS.gguf b/Llama-3-Unholy-8B-e4.IQ4_XS.gguf new file mode 100644 index 0000000..a5c08dd --- /dev/null +++ b/Llama-3-Unholy-8B-e4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19eb8a1188870030f06df58016a5ae383a08b458728a16b1c43873db39a94d97 +size 4484363360 diff --git a/Llama-3-Unholy-8B-e4.Q2_K.gguf b/Llama-3-Unholy-8B-e4.Q2_K.gguf new file mode 100644 index 0000000..647b1d5 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d738ba347b1afac61dda5b46594cc87f53fdafee513678c229a621718cb5a4 +size 3179132000 diff --git a/Llama-3-Unholy-8B-e4.Q3_K_L.gguf b/Llama-3-Unholy-8B-e4.Q3_K_L.gguf new file mode 100644 index 0000000..22a20d1 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a346244ee1fa43d42ac301ae036791cdd1309788c6279997602ca67231f62ed +size 4321956960 diff --git a/Llama-3-Unholy-8B-e4.Q3_K_M.gguf b/Llama-3-Unholy-8B-e4.Q3_K_M.gguf new file mode 100644 index 0000000..4359307 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a267f41c2aeebfdbdec78e7cf899e7c294de38184fba4f9a4eefdf317b58f25e +size 4018918496 diff --git a/Llama-3-Unholy-8B-e4.Q3_K_S.gguf b/Llama-3-Unholy-8B-e4.Q3_K_S.gguf new file mode 100644 index 0000000..4e83bce --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd8e7a3d44e530fe0282d33c393be579d15c8fd5ed4681d5967a40a0bcaded2 +size 3664499808 diff --git a/Llama-3-Unholy-8B-e4.Q4_K_M.gguf b/Llama-3-Unholy-8B-e4.Q4_K_M.gguf new file mode 100644 index 0000000..7af4fc1 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f27254b030c04d029f14f2380dbad28d627096ee245370ea21b700438b43f1 +size 4920734816 diff --git a/Llama-3-Unholy-8B-e4.Q4_K_S.gguf b/Llama-3-Unholy-8B-e4.Q4_K_S.gguf new file mode 100644 index 0000000..28fbd6b --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f650643c9453714cc7dd0978738c9bbd1a74378313610e390d67ebaf3a9bcbd +size 4692669536 diff --git a/Llama-3-Unholy-8B-e4.Q5_K_M.gguf b/Llama-3-Unholy-8B-e4.Q5_K_M.gguf new file mode 100644 index 0000000..c08c3f9 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138d1ea64fb5af3153fbb73e32caecad12ba9a15d5ba75db5fefa0ad97d04d90 +size 5732988000 diff --git a/Llama-3-Unholy-8B-e4.Q5_K_S.gguf b/Llama-3-Unholy-8B-e4.Q5_K_S.gguf new file mode 100644 index 0000000..0a6e3e6 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92f670ac736a6dcd7553fe45952c309ce8144d341ad18e7d1991e27bf6e567c +size 5599294560 diff --git a/Llama-3-Unholy-8B-e4.Q6_K.gguf b/Llama-3-Unholy-8B-e4.Q6_K.gguf new file mode 100644 index 0000000..31d8f26 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29431d385a897ee8583afc4c390d341c12fbd4cb8d834f4e08a80b7bc8297695 +size 6596007008 diff --git a/Llama-3-Unholy-8B-e4.Q8_0.gguf b/Llama-3-Unholy-8B-e4.Q8_0.gguf new file mode 100644 index 0000000..f8d7fa3 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91324b6cf6add775104bf5bf4f9e080f1571034632065a2f9035b24e3813a1c6 +size 8540771424 diff --git a/Llama-3-Unholy-8B-e4.f16.gguf b/Llama-3-Unholy-8B-e4.f16.gguf new file mode 100644 index 0000000..61185d7 --- /dev/null +++ b/Llama-3-Unholy-8B-e4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f626601d975b0f9f04c2b172f3fcfc52dd2b1261d4dc6416ab4607ae3926f81e +size 16068891744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a75bd6 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Undi95/Llama-3-Unholy-8B-e4 +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- not-for-all-audiences +- nsfw +--- +## About + + + + + + +static quants of https://huggingface.co/Undi95/Llama-3-Unholy-8B-e4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-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-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Unholy-8B-e4-GGUF/resolve/main/Llama-3-Unholy-8B-e4.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. + +