commit 044e49e2b30e7562ac795148b21679d05d240fa5 Author: ModelHub XC Date: Tue Jul 7 00:31:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AlphaMonarch-laser-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae59abd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +AlphaMonarch-laser.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.f16.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-laser.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AlphaMonarch-laser.IQ4_XS.gguf b/AlphaMonarch-laser.IQ4_XS.gguf new file mode 100644 index 0000000..911dee3 --- /dev/null +++ b/AlphaMonarch-laser.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f13cf02990fedfd2ee97dc7f801b2cea5684d57b26b7a28203769071e2b9b66 +size 3944389952 diff --git a/AlphaMonarch-laser.Q2_K.gguf b/AlphaMonarch-laser.Q2_K.gguf new file mode 100644 index 0000000..4547320 --- /dev/null +++ b/AlphaMonarch-laser.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3be18909f39881d3651935de38869bf39ed44e225cb42aec30e76766f722362 +size 2719243584 diff --git a/AlphaMonarch-laser.Q3_K_L.gguf b/AlphaMonarch-laser.Q3_K_L.gguf new file mode 100644 index 0000000..0b30d00 --- /dev/null +++ b/AlphaMonarch-laser.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17eeee6f65be771f9e6154975149212b3eb5fe738d5a4ecfdc36af3e0c191832 +size 3822026048 diff --git a/AlphaMonarch-laser.Q3_K_M.gguf b/AlphaMonarch-laser.Q3_K_M.gguf new file mode 100644 index 0000000..fcf33f6 --- /dev/null +++ b/AlphaMonarch-laser.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbcca9d15b554d4cc9bbd709e377865518562046bd284e9edd5062479014ef7 +size 3518987584 diff --git a/AlphaMonarch-laser.Q3_K_S.gguf b/AlphaMonarch-laser.Q3_K_S.gguf new file mode 100644 index 0000000..e9d1f78 --- /dev/null +++ b/AlphaMonarch-laser.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9642b8cb6967495809fca90d01d64d56ad5ab0844896ceac13aa4f5ab7b28b17 +size 3164568896 diff --git a/AlphaMonarch-laser.Q4_0_4_4.gguf b/AlphaMonarch-laser.Q4_0_4_4.gguf new file mode 100644 index 0000000..9ab5802 --- /dev/null +++ b/AlphaMonarch-laser.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4425e45e4f3a045e27d00efb0604181afa6bef7bd94255fe5ce578e39b797254 +size 4108918080 diff --git a/AlphaMonarch-laser.Q4_K_M.gguf b/AlphaMonarch-laser.Q4_K_M.gguf new file mode 100644 index 0000000..64cf4c9 --- /dev/null +++ b/AlphaMonarch-laser.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57fced3649fd25d19278629927907d499481cfb391c695ed593831d24a4db72b +size 4368440640 diff --git a/AlphaMonarch-laser.Q4_K_S.gguf b/AlphaMonarch-laser.Q4_K_S.gguf new file mode 100644 index 0000000..be6b283 --- /dev/null +++ b/AlphaMonarch-laser.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c0ad1e16f8ed079fea7e80c55cfee605aa1bac51b643c00fae1a7752fa7855 +size 4140375360 diff --git a/AlphaMonarch-laser.Q5_K_M.gguf b/AlphaMonarch-laser.Q5_K_M.gguf new file mode 100644 index 0000000..efae78b --- /dev/null +++ b/AlphaMonarch-laser.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8366f0a44198ffdf3f6e27b7ea9451f87acaa4026aac3424259cc9f5735000 +size 5131410752 diff --git a/AlphaMonarch-laser.Q5_K_S.gguf b/AlphaMonarch-laser.Q5_K_S.gguf new file mode 100644 index 0000000..958bf85 --- /dev/null +++ b/AlphaMonarch-laser.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce29f4b3beeef3b7d73975d184e6ba3e508f02395375c5b22eb223254493f4c +size 4997717312 diff --git a/AlphaMonarch-laser.Q6_K.gguf b/AlphaMonarch-laser.Q6_K.gguf new file mode 100644 index 0000000..e3d08cb --- /dev/null +++ b/AlphaMonarch-laser.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d595df32ce72bc6776ea775b40ef450ff1e11cae1bbe03a859483d0946abd2b5 +size 5942066496 diff --git a/AlphaMonarch-laser.Q8_0.gguf b/AlphaMonarch-laser.Q8_0.gguf new file mode 100644 index 0000000..e59b624 --- /dev/null +++ b/AlphaMonarch-laser.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c10063fef27e6c9957d4352f78eacdda3ce3c7796780ec1a9b568f68883d08 +size 7695859008 diff --git a/AlphaMonarch-laser.f16.gguf b/AlphaMonarch-laser.f16.gguf new file mode 100644 index 0000000..0056e76 --- /dev/null +++ b/AlphaMonarch-laser.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02110fbe8c60d67647893aa71fa0b1f1763ebabbd20c5ef4ec68493a9fd596a7 +size 14484733248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1b42069 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: abideen/AlphaMonarch-laser +datasets: +- argilla/OpenHermes2.5-dpo-binarized-alpha +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- generated_from_trainer +- axolotl +- mistral +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- distillation +--- +## About + + + + + + +static quants of https://huggingface.co/abideen/AlphaMonarch-laser + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AlphaMonarch-laser-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/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-laser-GGUF/resolve/main/AlphaMonarch-laser.f16.gguf) | f16 | 14.6 | 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. + +