commit f567252ef1eab034ac444d0422f4d3224ebc8283 Author: ModelHub XC Date: Wed Jul 1 15:34:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mahou-1.2a-llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9dc0cb0 --- /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 +Mahou-1.2a-llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mahou-1.2a-llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mahou-1.2a-llama3-8B.IQ3_M.gguf b/Mahou-1.2a-llama3-8B.IQ3_M.gguf new file mode 100644 index 0000000..f2fcf74 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46feb88aa136aa4f4c6571dd3e6002a31e974d56c55b98687c6bb606ea259eb1 +size 3784823488 diff --git a/Mahou-1.2a-llama3-8B.IQ3_S.gguf b/Mahou-1.2a-llama3-8B.IQ3_S.gguf new file mode 100644 index 0000000..a7fb354 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872e0217496ce6233061e970bce7bb2e8046b5686bfa102d1c776b1e5f9905e5 +size 3682325184 diff --git a/Mahou-1.2a-llama3-8B.IQ3_XS.gguf b/Mahou-1.2a-llama3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..71ccdf4 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb04665afb764efb0445438999540325578087281a5b5339a31e48edbd8055fa +size 3518747328 diff --git a/Mahou-1.2a-llama3-8B.IQ4_XS.gguf b/Mahou-1.2a-llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..4de5f94 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a21a0db693263481a42f95d13c3e89ee4fb9bff53fc32dceb2b1276afb43da +size 4484362944 diff --git a/Mahou-1.2a-llama3-8B.Q2_K.gguf b/Mahou-1.2a-llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..3c3ad60 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6e80264ea043edc4c6ebcbb4fc3cc266da70ae9f74beee8c3a2f4760e56bcc +size 3179131584 diff --git a/Mahou-1.2a-llama3-8B.Q3_K_L.gguf b/Mahou-1.2a-llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..f74920f --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8da44a4559082fbdf6f3493ef6c96df7b0ce7750f94fb03e1ab027c60cbd85 +size 4321956544 diff --git a/Mahou-1.2a-llama3-8B.Q3_K_M.gguf b/Mahou-1.2a-llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..d779175 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ba70d34ba9c6935a40793588a30fb8afa3eb65050e73ab818e5e6db1f7edcb +size 4018918080 diff --git a/Mahou-1.2a-llama3-8B.Q3_K_S.gguf b/Mahou-1.2a-llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..3c1d485 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e3fb06329189cfda750b6234aefa4f2aa26c4cb800b463ccfe2489b523698e +size 3664499392 diff --git a/Mahou-1.2a-llama3-8B.Q4_K_M.gguf b/Mahou-1.2a-llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..7b4bee5 --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b59b1eae6970b793a7350bf4ea40160cd61843d6b16c820a3d417754a5e7b4f +size 4920734400 diff --git a/Mahou-1.2a-llama3-8B.Q4_K_S.gguf b/Mahou-1.2a-llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..ee2c86e --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba67d35da270bd5fb0ef2c3a1840cc1e647a0ca0d6e6f54b85b873b5e1641b5 +size 4692669120 diff --git a/Mahou-1.2a-llama3-8B.Q5_K_M.gguf b/Mahou-1.2a-llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..cac5f8f --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8959d76e9908c7b1bc0526cdda72e7a4f76a46858753652b1486899e8d03ec +size 5732987584 diff --git a/Mahou-1.2a-llama3-8B.Q5_K_S.gguf b/Mahou-1.2a-llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..9ede6ed --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dbcdadbb06205bfdc11c2fefb730f3ccb4a0e3f52f1c7f7d2d0a78b95febdac +size 5599294144 diff --git a/Mahou-1.2a-llama3-8B.Q6_K.gguf b/Mahou-1.2a-llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..95a9e4a --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed8eaa40718ba3f215ff6cf2d508a497c5573477a8eb3c2907842218243eac9 +size 6596006592 diff --git a/Mahou-1.2a-llama3-8B.Q8_0.gguf b/Mahou-1.2a-llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..6fbef9e --- /dev/null +++ b/Mahou-1.2a-llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06afe1547071f020fda2bc2888dc1ecbc34ba7d51882c914eb3bc772bfd70077 +size 8540771008 diff --git a/Mahou-1.2a-llama3-8B.f16.gguf b/Mahou-1.2a-llama3-8B.f16.gguf new file mode 100644 index 0000000..9327f6c --- /dev/null +++ b/Mahou-1.2a-llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df279f9073902fc4da03640d09a2357dbc1c5d21c85262f048a51c580384558 +size 16068891328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7257dc7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: flammenai/Mahou-1.2a-llama3-8B +datasets: +- flammenai/FlameMix-DPO-v1 +- 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-1.2a-llama3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mahou-1.2a-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-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-llama3-8B-GGUF/resolve/main/Mahou-1.2a-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. + +