commit 18f4e88d84d8a72edb7c8e5a2912cf4e2d290961 Author: ModelHub XC Date: Fri Jun 12 06:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mahou-1.2-llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cbda779 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Mahou-1.2-llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2-llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mahou-1.2-llama3-8B.IQ3_M.gguf b/Mahou-1.2-llama3-8B.IQ3_M.gguf new file mode 100644 index 0000000..bf79b0c --- /dev/null +++ b/Mahou-1.2-llama3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c582498441c38f8343ed614a6451df11018ef0969784aefbecd4b1514ed947 +size 3784823488 diff --git a/Mahou-1.2-llama3-8B.IQ3_S.gguf b/Mahou-1.2-llama3-8B.IQ3_S.gguf new file mode 100644 index 0000000..884c15b --- /dev/null +++ b/Mahou-1.2-llama3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba7073c00c88fa33d4a288152958eb600630840340a3c3f00832459d69c1446 +size 3682325184 diff --git a/Mahou-1.2-llama3-8B.IQ3_XS.gguf b/Mahou-1.2-llama3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..59ab0d8 --- /dev/null +++ b/Mahou-1.2-llama3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b92c4d4c8a62647fb6645143bead6adcc90b3f77746ac92cae5ef67537338f4 +size 3518747328 diff --git a/Mahou-1.2-llama3-8B.IQ4_XS.gguf b/Mahou-1.2-llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..08c5e20 --- /dev/null +++ b/Mahou-1.2-llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20184f06fefd2f0529fe554f7f9c05901df5bbe79c907e221e0e2c22f45e413d +size 4484362944 diff --git a/Mahou-1.2-llama3-8B.Q2_K.gguf b/Mahou-1.2-llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..ecbeb37 --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37e0ba1a7924e646c80e4351c2ff63720b9f679783f2c58de9092d8e87c3cfe +size 3179131584 diff --git a/Mahou-1.2-llama3-8B.Q3_K_L.gguf b/Mahou-1.2-llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..50c20b1 --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79298d5a0a67bb991462f231a1e348ea471390b4eb080d9d0f887c1a5db02571 +size 4321956544 diff --git a/Mahou-1.2-llama3-8B.Q3_K_M.gguf b/Mahou-1.2-llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..c8dca4f --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7295b89ca09a663389fdf565cc1f3ea58ba907953213d222821e5469938580 +size 4018918080 diff --git a/Mahou-1.2-llama3-8B.Q3_K_S.gguf b/Mahou-1.2-llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..e16e047 --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c407468b0f4cf93cde9391a6b74b0337a6d9f6da99dca2809255da94d7bde1f +size 3664499392 diff --git a/Mahou-1.2-llama3-8B.Q4_K_M.gguf b/Mahou-1.2-llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..8aa5fd0 --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476d276fd5df58c88b85937eeb9581c4184319939ad6d3f283c3b6f932f563a1 +size 4920734400 diff --git a/Mahou-1.2-llama3-8B.Q4_K_S.gguf b/Mahou-1.2-llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..cb6f7da --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a8cf61b23cc296b1751528018db3945d3c130670e7b4e6b64776bc676755a54 +size 4692669120 diff --git a/Mahou-1.2-llama3-8B.Q5_K_M.gguf b/Mahou-1.2-llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..9eb6779 --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3c724c768886bd9914d2e12b85c0c5511ca88a9eac650f376fd22cb7adeaea +size 5732987584 diff --git a/Mahou-1.2-llama3-8B.Q5_K_S.gguf b/Mahou-1.2-llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..668224f --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14522c318a85d22974961695e3827d231776a4b4261d1f2c929ca0ab7df62484 +size 5599294144 diff --git a/Mahou-1.2-llama3-8B.Q6_K.gguf b/Mahou-1.2-llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..47a4a20 --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc9559de12cd5cdc3f01275de798453a9bbe409286db2b62127847daca6467c +size 6596006592 diff --git a/Mahou-1.2-llama3-8B.Q8_0.gguf b/Mahou-1.2-llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..085cfae --- /dev/null +++ b/Mahou-1.2-llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18657ba37f1984124be84d438e183a4a44b8cb1851f35eb7532e2392b4ccb25f +size 8540771008 diff --git a/Mahou-1.2-llama3-8B.f16.gguf b/Mahou-1.2-llama3-8B.f16.gguf new file mode 100644 index 0000000..1fb0329 --- /dev/null +++ b/Mahou-1.2-llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39846ffec74a38926507062469ff3d1b149beda11e1128d2dae046fb03996a6 +size 16068891328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d45916b --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: flammenai/Mahou-1.2-llama3-8B +datasets: +- flammenai/Grill-preprod-v1_chatML +- flammenai/Grill-preprod-v2_chatML +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + +static quants of https://huggingface.co/flammenai/Mahou-1.2-llama3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-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/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2-llama3-8B-GGUF/resolve/main/Mahou-1.2-llama3-8B.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. + +