commit e0eee83f8cdf3379f42cb9b56837072713c5479a Author: ModelHub XC Date: Sun Apr 12 15:52:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2af1fc7 --- /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-3-8B-Magpie-Pro-SFT-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_M.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_M.gguf new file mode 100644 index 0000000..de6bc26 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4430bf36a8003a42dceea4febaeaefa2500a39bf1180dcb8a71d5a60aef6c77 +size 3784823584 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_S.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_S.gguf new file mode 100644 index 0000000..d1e7e31 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91d82231b6fb405b26e349d6608b6378ba599ab736549ad6fedade7d27bf723 +size 3682325280 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_XS.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_XS.gguf new file mode 100644 index 0000000..71a19ce --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf2de11cb8dfc32cbe38757e0f65213785480561ff981d226d5aebc99031760f +size 3518747424 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ4_XS.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..a1c034c --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4157483646af2da7d83ede717e638f1fdf73736a2bdad68b29c6ab86ff0ab3 +size 4484363040 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q2_K.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q2_K.gguf new file mode 100644 index 0000000..9f685b8 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c406c4d4ed22c0a8982edcc833e2d1334c944b7554e80c8f69fe86874ea5a69d +size 3179131680 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_L.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..aafbacf --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff7f5f53d98a3db78cc7e3b51f9bf4b6bea5a6c6cd65d26e4ebc1311ad97e58 +size 4321956640 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_M.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..52e8178 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53c282d65245dfb5f7c98b9d777fa0d345e505e0d8f0da96d71c92ccbf3e324 +size 4018918176 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_S.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..5b2924e --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104d66b08f604af87207e8228c4869ba5db5e1ec5734f9387a9ced82e58f2188 +size 3664499488 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_M.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..662e0af --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412ebe86d68d5f2eac1143d4ac8063fdec2576f62c1b951c5d21ccd76b6ea5e8 +size 4920734496 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_S.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..24168eb --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ce437d011420f73703641655848897cf0c310f85cd3b3f62951098a4ae8076 +size 4692669216 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_M.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..172b73a --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f117f02246322fa18e91e16cd1d4962f03ed0db28c0802e6e25515525f8dc1e +size 5732987680 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_S.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..186dca3 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1541d816c88b9551e1c18ea2e9d35fe68e47b0fd480dd34037e18ab1fc3bdda +size 5599294240 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q6_K.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q6_K.gguf new file mode 100644 index 0000000..565ee04 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b056f6a8b6df93e225416f96162bca73ea086a4471031d8a9b51b9cdf4a48e +size 6596006688 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q8_0.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q8_0.gguf new file mode 100644 index 0000000..8c02f99 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f1057a53abc0eb96d6732e93a5c3f8c035f9e5301f622002fe899e97b1aa1b +size 8540771104 diff --git a/Llama-3-8B-Magpie-Pro-SFT-v0.1.f16.gguf b/Llama-3-8B-Magpie-Pro-SFT-v0.1.f16.gguf new file mode 100644 index 0000000..2770a73 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-SFT-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b53657ab7d3a49f720dfb80761e427237d2ddb50e9917d449e35532afa171f5 +size 16068891424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a5a2c3 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-300K-v0.1 +datasets: +- Magpie-Align/Magpie-Pro-300K-Filtered +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- axolotl +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-300K-v0.1 + + +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-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-SFT-v0.1-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-SFT-v0.1.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. + +