commit 453483c37e461db2fc16f9e6e16ee877cb7aed0f Author: ModelHub XC Date: Mon Aug 10 11:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-NeuralMahou-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..441b4ca --- /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 +llama-3-NeuralMahou-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-NeuralMahou-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..91c1748 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: lemon07r/llama-3-NeuralMahou-8b +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/lemon07r/llama-3-NeuralMahou-8b + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-NeuralMahou-8b-GGUF/resolve/main/llama-3-NeuralMahou-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. + + diff --git a/llama-3-NeuralMahou-8b.IQ3_M.gguf b/llama-3-NeuralMahou-8b.IQ3_M.gguf new file mode 100644 index 0000000..a5fb3d4 --- /dev/null +++ b/llama-3-NeuralMahou-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4ea7d8c80ab99288b4979518268a273c6f2e094a379a869e810ba5d8dd2be9 +size 3784823104 diff --git a/llama-3-NeuralMahou-8b.IQ3_S.gguf b/llama-3-NeuralMahou-8b.IQ3_S.gguf new file mode 100644 index 0000000..aaac794 --- /dev/null +++ b/llama-3-NeuralMahou-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08154176d3189823dcac65d392e56bc67e72daa1ea2059543a7d87aad700e85c +size 3682324800 diff --git a/llama-3-NeuralMahou-8b.IQ3_XS.gguf b/llama-3-NeuralMahou-8b.IQ3_XS.gguf new file mode 100644 index 0000000..e979ace --- /dev/null +++ b/llama-3-NeuralMahou-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9c2915797248c328f063b8652272789808110bfc5bcb869433662dbd1a5205 +size 3518746944 diff --git a/llama-3-NeuralMahou-8b.IQ4_XS.gguf b/llama-3-NeuralMahou-8b.IQ4_XS.gguf new file mode 100644 index 0000000..e878c19 --- /dev/null +++ b/llama-3-NeuralMahou-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ab67271891d7975fafcda9d8be3288bf3a1ba1d2ed1d64e2b48942f42c80cb +size 4484362560 diff --git a/llama-3-NeuralMahou-8b.Q2_K.gguf b/llama-3-NeuralMahou-8b.Q2_K.gguf new file mode 100644 index 0000000..ed5627e --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b713c35c5ae789ae2debdd7dc3ddbab33d4569919218916cd2dea5784b8f15c +size 3179131200 diff --git a/llama-3-NeuralMahou-8b.Q3_K_L.gguf b/llama-3-NeuralMahou-8b.Q3_K_L.gguf new file mode 100644 index 0000000..0004c4b --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92cfb0d6b7251fe76320250b976ab0fb5fdcf288b4921d1e0404f40e8bc6951e +size 4321956160 diff --git a/llama-3-NeuralMahou-8b.Q3_K_M.gguf b/llama-3-NeuralMahou-8b.Q3_K_M.gguf new file mode 100644 index 0000000..fa15435 --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b57ea6ab4742dcfa419e53ec437cd0e94c99e3c2cd0a14b8089cae331e7619d +size 4018917696 diff --git a/llama-3-NeuralMahou-8b.Q3_K_S.gguf b/llama-3-NeuralMahou-8b.Q3_K_S.gguf new file mode 100644 index 0000000..45acb40 --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f9386377f99e8e481d0d39723e7921d95c5e647e915d9a3e1029f49132bc1c +size 3664499008 diff --git a/llama-3-NeuralMahou-8b.Q4_K_M.gguf b/llama-3-NeuralMahou-8b.Q4_K_M.gguf new file mode 100644 index 0000000..d9a1631 --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9e68f1fc9ccde5e9d0562ff4faecf1912c8dbd1ffd4ef04d9c1fb95c6bdab2 +size 4920734016 diff --git a/llama-3-NeuralMahou-8b.Q4_K_S.gguf b/llama-3-NeuralMahou-8b.Q4_K_S.gguf new file mode 100644 index 0000000..921bedc --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf25e4a262be49c92657a5d9da08dc896241209926fdd4d019c2913505e8600 +size 4692668736 diff --git a/llama-3-NeuralMahou-8b.Q5_K_M.gguf b/llama-3-NeuralMahou-8b.Q5_K_M.gguf new file mode 100644 index 0000000..d1f1704 --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10efc4a626d2a2c6837001a8818028a92c90d40c1c88660146f2e38566644ff3 +size 5732987200 diff --git a/llama-3-NeuralMahou-8b.Q5_K_S.gguf b/llama-3-NeuralMahou-8b.Q5_K_S.gguf new file mode 100644 index 0000000..6a0fb95 --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbbe91f735845bc16a6cf2c28bc10fca5266af6dec990b14670ace6dfd63529 +size 5599293760 diff --git a/llama-3-NeuralMahou-8b.Q6_K.gguf b/llama-3-NeuralMahou-8b.Q6_K.gguf new file mode 100644 index 0000000..e80f7a0 --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6603326cc9609e931247ba9794d7efa7d3135c2bdfe62ff84030633ae3f61eac +size 6596006208 diff --git a/llama-3-NeuralMahou-8b.Q8_0.gguf b/llama-3-NeuralMahou-8b.Q8_0.gguf new file mode 100644 index 0000000..c4fd58e --- /dev/null +++ b/llama-3-NeuralMahou-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d05f9e6b3021917d832de53f1a8f76d1fd1e4b27c67e12fcda6c6002b1471c0b +size 8540770624 diff --git a/llama-3-NeuralMahou-8b.f16.gguf b/llama-3-NeuralMahou-8b.f16.gguf new file mode 100644 index 0000000..2ba0053 --- /dev/null +++ b/llama-3-NeuralMahou-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eaed6576ea2d53b9b92b085d114ae68f50a40bad48fe7d7ce3701a33f996053 +size 16068890944