commit e40b3e06570eb8b924053847c5396a312a7db4f3 Author: ModelHub XC Date: Sat Sep 12 14:48:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-darktune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aa0a2f7 --- /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 +llama3-8b-darktune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-darktune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f95bd61 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Hastagaras/llama3-8b-darktune +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + +static quants of https://huggingface.co/Hastagaras/llama3-8b-darktune + + +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/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-darktune-GGUF/resolve/main/llama3-8b-darktune.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/llama3-8b-darktune.IQ3_M.gguf b/llama3-8b-darktune.IQ3_M.gguf new file mode 100644 index 0000000..97a7180 --- /dev/null +++ b/llama3-8b-darktune.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57a45a611eecf33414a1d4f642a568c5e2f093d67ff499e5b2c465d153e46e0 +size 3784823136 diff --git a/llama3-8b-darktune.IQ3_S.gguf b/llama3-8b-darktune.IQ3_S.gguf new file mode 100644 index 0000000..77d94ff --- /dev/null +++ b/llama3-8b-darktune.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864dd1b6d0243190166015f142415a8a6d35e89ec50eba8ee1f7cc07475ca4a4 +size 3682324832 diff --git a/llama3-8b-darktune.IQ3_XS.gguf b/llama3-8b-darktune.IQ3_XS.gguf new file mode 100644 index 0000000..47d85ec --- /dev/null +++ b/llama3-8b-darktune.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d0a78a36cbf223f78ea4a610c0d94e7cc4d42260ef7c851e607c7b9bdfe5ac +size 3518746976 diff --git a/llama3-8b-darktune.IQ4_XS.gguf b/llama3-8b-darktune.IQ4_XS.gguf new file mode 100644 index 0000000..9b70c3d --- /dev/null +++ b/llama3-8b-darktune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808704265053799d570800082bc14e19104d6d1f7f6829f159a4978523aec31c +size 4484362592 diff --git a/llama3-8b-darktune.Q2_K.gguf b/llama3-8b-darktune.Q2_K.gguf new file mode 100644 index 0000000..e8d4727 --- /dev/null +++ b/llama3-8b-darktune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e513046ba72d3876f80dcb28a85f0dc6b107a8306bce51d10dfd8e727609609 +size 3179131232 diff --git a/llama3-8b-darktune.Q3_K_L.gguf b/llama3-8b-darktune.Q3_K_L.gguf new file mode 100644 index 0000000..0836397 --- /dev/null +++ b/llama3-8b-darktune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74270e40c9dfb49e3b3ceaea59cbc2610aa41e8794d32ecdb04d91914d950b39 +size 4321956192 diff --git a/llama3-8b-darktune.Q3_K_M.gguf b/llama3-8b-darktune.Q3_K_M.gguf new file mode 100644 index 0000000..bc8749d --- /dev/null +++ b/llama3-8b-darktune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a808095f366b56d16573d43b88898e0907639387613ee03a4a6b60cc81aca322 +size 4018917728 diff --git a/llama3-8b-darktune.Q3_K_S.gguf b/llama3-8b-darktune.Q3_K_S.gguf new file mode 100644 index 0000000..3d1ff8e --- /dev/null +++ b/llama3-8b-darktune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c951bc260c6eaf49e1540fa95cdddc89c47fd9d59a4706ff0e4cbe99af0296 +size 3664499040 diff --git a/llama3-8b-darktune.Q4_K_M.gguf b/llama3-8b-darktune.Q4_K_M.gguf new file mode 100644 index 0000000..f4d907a --- /dev/null +++ b/llama3-8b-darktune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aad9e0535644e5fbdf13786a07b7040a1da3a5d4aaba681628effefcdd4fcae +size 4920734048 diff --git a/llama3-8b-darktune.Q4_K_S.gguf b/llama3-8b-darktune.Q4_K_S.gguf new file mode 100644 index 0000000..5a3b54b --- /dev/null +++ b/llama3-8b-darktune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd6ab8e99dbba9f43df04be6cb7da7b3c30c662645eafcfdcf359457cf233833 +size 4692668768 diff --git a/llama3-8b-darktune.Q5_K_M.gguf b/llama3-8b-darktune.Q5_K_M.gguf new file mode 100644 index 0000000..e63aef5 --- /dev/null +++ b/llama3-8b-darktune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75c23fc40cb6168d26e3a7154bc3c709d00a083daf77964e6d5e0fecd96ec2f +size 5732987232 diff --git a/llama3-8b-darktune.Q5_K_S.gguf b/llama3-8b-darktune.Q5_K_S.gguf new file mode 100644 index 0000000..dd65b3e --- /dev/null +++ b/llama3-8b-darktune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48acfd93eddbd60da1d798e614452c8d0ccbcc00b9ef93700091f022c7e50bbf +size 5599293792 diff --git a/llama3-8b-darktune.Q6_K.gguf b/llama3-8b-darktune.Q6_K.gguf new file mode 100644 index 0000000..b791c8a --- /dev/null +++ b/llama3-8b-darktune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd5871515679df81e2c6481458360dca99494775c0d7fd65406be8c9beff7028 +size 6596006240 diff --git a/llama3-8b-darktune.Q8_0.gguf b/llama3-8b-darktune.Q8_0.gguf new file mode 100644 index 0000000..2278da5 --- /dev/null +++ b/llama3-8b-darktune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8619b463ae3a446929d0df6053fd524334d96d7209af0ac350d219acda3aa903 +size 8540770656 diff --git a/llama3-8b-darktune.f16.gguf b/llama3-8b-darktune.f16.gguf new file mode 100644 index 0000000..f15a7cb --- /dev/null +++ b/llama3-8b-darktune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20556d3d8acfe6b795fea64ae733bd0cb9cdd6d3713c5a113d579ee6e449967 +size 16068890976