commit 1dd85a8c30540fd37d893ff07cc3bc5bc934d4d8 Author: ModelHub XC Date: Thu Aug 6 00:13:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed843d6 --- /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 +Llama3.1-DilemmaDeluxe-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DilemmaDeluxe-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-DilemmaDeluxe-8B.IQ4_XS.gguf b/Llama3.1-DilemmaDeluxe-8B.IQ4_XS.gguf new file mode 100644 index 0000000..969546d --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321c6606ad15d55f3f747b7a42c4f67fc1ec75f441875c1233a4593d71779a9c +size 4484364192 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q2_K.gguf b/Llama3.1-DilemmaDeluxe-8B.Q2_K.gguf new file mode 100644 index 0000000..d2366df --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdbb247441efb0e8ddf42ef4165c21e11454af07febca4e640a31f0e0504fef9 +size 3179132832 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q3_K_L.gguf b/Llama3.1-DilemmaDeluxe-8B.Q3_K_L.gguf new file mode 100644 index 0000000..ce95d87 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33b29aeaa403e4fa0ab2287b485cde3e04d5b5848e47f27d2a10d329d44f435 +size 4321957792 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q3_K_M.gguf b/Llama3.1-DilemmaDeluxe-8B.Q3_K_M.gguf new file mode 100644 index 0000000..81fd208 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53604f261af2c660917d7cf302d73854efcb52afcb59f1dcee234862dc16c1a +size 4018919328 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q3_K_S.gguf b/Llama3.1-DilemmaDeluxe-8B.Q3_K_S.gguf new file mode 100644 index 0000000..9b0c426 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e257ce0a3cd2b65b00eb316aa554d087677aadac445aeb445268205683061e98 +size 3664500640 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q4_K_M.gguf b/Llama3.1-DilemmaDeluxe-8B.Q4_K_M.gguf new file mode 100644 index 0000000..e904391 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f982131699ac70c60d46a9bff879b6c861e27342ca53cd16a722cb02576d13 +size 4920735648 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q4_K_S.gguf b/Llama3.1-DilemmaDeluxe-8B.Q4_K_S.gguf new file mode 100644 index 0000000..db19436 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:722a3cce4b8e73ec4c7e168a7c644d6da549385b522d5b2205a5969911f05b22 +size 4692670368 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q5_K_M.gguf b/Llama3.1-DilemmaDeluxe-8B.Q5_K_M.gguf new file mode 100644 index 0000000..ecb5aff --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364f7cc8814e5dfbb72dc8a65860516cef277b9bf1e417c44e830646b822a16b +size 5732988832 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q5_K_S.gguf b/Llama3.1-DilemmaDeluxe-8B.Q5_K_S.gguf new file mode 100644 index 0000000..bbc3d70 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd3352ae50d9e5255019a3225e5af01b1e4b16f5be70c6fa0c35c60a159f7dd +size 5599295392 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q6_K.gguf b/Llama3.1-DilemmaDeluxe-8B.Q6_K.gguf new file mode 100644 index 0000000..3bd317a --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e4c47df568ef5e7b2624ebdda8ec3f38bb168e83e38738dc1bb45e6e0cbfd7d +size 6596007840 diff --git a/Llama3.1-DilemmaDeluxe-8B.Q8_0.gguf b/Llama3.1-DilemmaDeluxe-8B.Q8_0.gguf new file mode 100644 index 0000000..66ea917 --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c04e9d9d548006c62dfed68454c7fa374d7ea26de865f3b40db73600f880a8 +size 8540772256 diff --git a/Llama3.1-DilemmaDeluxe-8B.f16.gguf b/Llama3.1-DilemmaDeluxe-8B.f16.gguf new file mode 100644 index 0000000..748ec7d --- /dev/null +++ b/Llama3.1-DilemmaDeluxe-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0cb07510b4a54f7368ed107a3da9200e42e452fc12ba454c5e4380b85bb2eb8 +size 16068892576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00f8db5 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Yuma42/Llama3.1-DilemmaDeluxe-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Yuma42/Llama3.1-DeepDilemma-V1-8B +- Yuma42/Llama3.1-DeluXeOne-8B +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yuma42/Llama3.1-DilemmaDeluxe-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-DilemmaDeluxe-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-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/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DilemmaDeluxe-8B-GGUF/resolve/main/Llama3.1-DilemmaDeluxe-8B.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. + +