commit f3c523edb13af7059386b8c04b29f0fd8568eae5 Author: ModelHub XC Date: Tue Jul 7 00:21:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AlphaMonarch-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..61493fd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMonarch-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AlphaMonarch-7B.IQ3_M.gguf b/AlphaMonarch-7B.IQ3_M.gguf new file mode 100644 index 0000000..654fdd1 --- /dev/null +++ b/AlphaMonarch-7B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbb2a27fab48eec018a13594ee0268ff766b22e9e84bcdb8fbdcb4324e5e1f7 +size 3284892960 diff --git a/AlphaMonarch-7B.IQ3_S.gguf b/AlphaMonarch-7B.IQ3_S.gguf new file mode 100644 index 0000000..51daebd --- /dev/null +++ b/AlphaMonarch-7B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2f882e3fa7c708cfbb02f289481c60c0a10e9f20bb7176d5b024f45a5e339e +size 3182394656 diff --git a/AlphaMonarch-7B.IQ3_XS.gguf b/AlphaMonarch-7B.IQ3_XS.gguf new file mode 100644 index 0000000..4d0aff9 --- /dev/null +++ b/AlphaMonarch-7B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181f41abb0fd246c75e8ac137be2817ff64670aa58fdcf89cda188906986cc8e +size 3018816800 diff --git a/AlphaMonarch-7B.IQ4_XS.gguf b/AlphaMonarch-7B.IQ4_XS.gguf new file mode 100644 index 0000000..b403770 --- /dev/null +++ b/AlphaMonarch-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f21775c76fb645e4d3f9ec36a182615d290855bda3e59f3502458d7159b96c6 +size 3944389920 diff --git a/AlphaMonarch-7B.Q2_K.gguf b/AlphaMonarch-7B.Q2_K.gguf new file mode 100644 index 0000000..ba2256e --- /dev/null +++ b/AlphaMonarch-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b6f7e63a33892129359ce7dff23ab728f661ad946bc2d9aa00c2468dbf7aea +size 2719243552 diff --git a/AlphaMonarch-7B.Q3_K_L.gguf b/AlphaMonarch-7B.Q3_K_L.gguf new file mode 100644 index 0000000..b6d3feb --- /dev/null +++ b/AlphaMonarch-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe990432984fd39edbd637239d43a920d46ef0f8c6e37d229ffc427588bab796 +size 3822026016 diff --git a/AlphaMonarch-7B.Q3_K_M.gguf b/AlphaMonarch-7B.Q3_K_M.gguf new file mode 100644 index 0000000..3061751 --- /dev/null +++ b/AlphaMonarch-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f9f7b8a581007ed4a0ee7f4dedc34709a3ec62f3ceb0fe1a730754262544f2 +size 3518987552 diff --git a/AlphaMonarch-7B.Q3_K_S.gguf b/AlphaMonarch-7B.Q3_K_S.gguf new file mode 100644 index 0000000..c0bced2 --- /dev/null +++ b/AlphaMonarch-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37504a6892574c7caae63b782a554d2d26d3836cb9ebc2b78fb5fe67e386d4f1 +size 3164568864 diff --git a/AlphaMonarch-7B.Q4_K_M.gguf b/AlphaMonarch-7B.Q4_K_M.gguf new file mode 100644 index 0000000..8ada14d --- /dev/null +++ b/AlphaMonarch-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8e726aeaee7f8624f5d73e6b9ede4de27d5835b9eb4c23580050548ce7fad0 +size 4368440608 diff --git a/AlphaMonarch-7B.Q4_K_S.gguf b/AlphaMonarch-7B.Q4_K_S.gguf new file mode 100644 index 0000000..2ba9551 --- /dev/null +++ b/AlphaMonarch-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6fc406d73a1689fe595f41c9eaf60586b916f775d614bc54af1f01827c80a1c +size 4140375328 diff --git a/AlphaMonarch-7B.Q5_K_M.gguf b/AlphaMonarch-7B.Q5_K_M.gguf new file mode 100644 index 0000000..870155e --- /dev/null +++ b/AlphaMonarch-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4d997d65fdcdd9637379b565e3fae908bac648e13221d633ff22d8f34d9b7d +size 5131410720 diff --git a/AlphaMonarch-7B.Q5_K_S.gguf b/AlphaMonarch-7B.Q5_K_S.gguf new file mode 100644 index 0000000..da7cf75 --- /dev/null +++ b/AlphaMonarch-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37f55560ee6d29614b7b0ecf1d86792e376c522fae0f39a0e5d4a8706e815be6 +size 4997717280 diff --git a/AlphaMonarch-7B.Q6_K.gguf b/AlphaMonarch-7B.Q6_K.gguf new file mode 100644 index 0000000..06f4d97 --- /dev/null +++ b/AlphaMonarch-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3139694b9b209c81e0bb91f394ba96c278f381951d0b37e17bb2031a1395ca9b +size 5942066464 diff --git a/AlphaMonarch-7B.Q8_0.gguf b/AlphaMonarch-7B.Q8_0.gguf new file mode 100644 index 0000000..0ca9e6f --- /dev/null +++ b/AlphaMonarch-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed15ff8c213761eff72856b0e38711c208b0bcc09a37e0be8c03f591600be6c8 +size 7695858976 diff --git a/AlphaMonarch-7B.f16.gguf b/AlphaMonarch-7B.f16.gguf new file mode 100644 index 0000000..05e9fed --- /dev/null +++ b/AlphaMonarch-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e98a8b0ff251f78900fcf9912479311f96481fb2305914851dcef348bfc7e16 +size 14484733216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e3c8484 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: mlabonne/AlphaMonarch-7B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- merge +- lazymergekit +- dpo +- rlhf +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/AlphaMonarch-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AlphaMonarch-7B-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-7B-GGUF/resolve/main/AlphaMonarch-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMonarch-7B-GGUF/resolve/main/AlphaMonarch-7B.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. + +