commit 8bdd9540e3bb58dbd0eb7f14ee060e62d95e6ece Author: ModelHub XC Date: Sat Aug 8 11:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-ProTrix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..514f385 --- /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-ProTrix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ProTrix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-ProTrix.IQ3_M.gguf b/Llama-3-ProTrix.IQ3_M.gguf new file mode 100644 index 0000000..7213671 --- /dev/null +++ b/Llama-3-ProTrix.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e159300e638fa705b2c4fd27576b93a84047eeaf216de5a913ee548425afb421 +size 3784823072 diff --git a/Llama-3-ProTrix.IQ3_S.gguf b/Llama-3-ProTrix.IQ3_S.gguf new file mode 100644 index 0000000..353ad3c --- /dev/null +++ b/Llama-3-ProTrix.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b81ca859b606eab2bf2870d4ccda7660bc01e60e8665b30366be6baf7b8ffb87 +size 3682324768 diff --git a/Llama-3-ProTrix.IQ3_XS.gguf b/Llama-3-ProTrix.IQ3_XS.gguf new file mode 100644 index 0000000..8baf52e --- /dev/null +++ b/Llama-3-ProTrix.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:118f651774092e88e5ba8e2277395ef40d6391971cfd318037ef04547a07a5b9 +size 3518746912 diff --git a/Llama-3-ProTrix.IQ4_XS.gguf b/Llama-3-ProTrix.IQ4_XS.gguf new file mode 100644 index 0000000..4b9c14d --- /dev/null +++ b/Llama-3-ProTrix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56dad8a3898b27e8b1e090b8c3b806e61e8ac7f74bfa8880ada0382abd82f9fa +size 4484362528 diff --git a/Llama-3-ProTrix.Q2_K.gguf b/Llama-3-ProTrix.Q2_K.gguf new file mode 100644 index 0000000..e752d4b --- /dev/null +++ b/Llama-3-ProTrix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3ee15f19bfcc30bd3335fc0a63f939c51946a2eff7fc560fc270cdb3785ee3 +size 3179131168 diff --git a/Llama-3-ProTrix.Q3_K_L.gguf b/Llama-3-ProTrix.Q3_K_L.gguf new file mode 100644 index 0000000..d650cf6 --- /dev/null +++ b/Llama-3-ProTrix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c867ce66656861ed5f2120a840af4af94599d220e4eaa17379f2bd243713c3 +size 4321956128 diff --git a/Llama-3-ProTrix.Q3_K_M.gguf b/Llama-3-ProTrix.Q3_K_M.gguf new file mode 100644 index 0000000..453c47f --- /dev/null +++ b/Llama-3-ProTrix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49854e077c0e17d9beaf70f2a56bfba17c288211a5406dbda378f1f927f329c2 +size 4018917664 diff --git a/Llama-3-ProTrix.Q3_K_S.gguf b/Llama-3-ProTrix.Q3_K_S.gguf new file mode 100644 index 0000000..67a37b5 --- /dev/null +++ b/Llama-3-ProTrix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ee6c502213cdf52309748e5268f60fde7263ca6374d3fd785b347ae133c799 +size 3664498976 diff --git a/Llama-3-ProTrix.Q4_K_M.gguf b/Llama-3-ProTrix.Q4_K_M.gguf new file mode 100644 index 0000000..673a101 --- /dev/null +++ b/Llama-3-ProTrix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c175c7eeca207b270e9343d26254d0972868147e8ee676b96a8344b73e30c0 +size 4920733984 diff --git a/Llama-3-ProTrix.Q4_K_S.gguf b/Llama-3-ProTrix.Q4_K_S.gguf new file mode 100644 index 0000000..a23bf89 --- /dev/null +++ b/Llama-3-ProTrix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebebe54be8fda55bf2dbdf369d5cd7fde1e9dcc99a1031fde9779c9e52a7739 +size 4692668704 diff --git a/Llama-3-ProTrix.Q5_K_M.gguf b/Llama-3-ProTrix.Q5_K_M.gguf new file mode 100644 index 0000000..30d01da --- /dev/null +++ b/Llama-3-ProTrix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981bdf4be5b645f19072e463abd15c39ee34010238b753b4a5f5693713dddd71 +size 5732987168 diff --git a/Llama-3-ProTrix.Q5_K_S.gguf b/Llama-3-ProTrix.Q5_K_S.gguf new file mode 100644 index 0000000..bca6bee --- /dev/null +++ b/Llama-3-ProTrix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a83a43ff6923b186d81ae68ab4defedcd2cdfb7e504b032a78b65d5a47becbd +size 5599293728 diff --git a/Llama-3-ProTrix.Q6_K.gguf b/Llama-3-ProTrix.Q6_K.gguf new file mode 100644 index 0000000..90e7887 --- /dev/null +++ b/Llama-3-ProTrix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f732c9967957aa3c19fdb040224780eb675c33cff4cfa03b11d4fe50dd4a3970 +size 6596006176 diff --git a/Llama-3-ProTrix.Q8_0.gguf b/Llama-3-ProTrix.Q8_0.gguf new file mode 100644 index 0000000..e807ab4 --- /dev/null +++ b/Llama-3-ProTrix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f623adb7e9a57f6dc95ed20ffafa5c2369258625d89ebda162240a1ac6fd520 +size 8540770592 diff --git a/Llama-3-ProTrix.f16.gguf b/Llama-3-ProTrix.f16.gguf new file mode 100644 index 0000000..a236eab --- /dev/null +++ b/Llama-3-ProTrix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14130a34c49cab555fd57e2c30c1ddc07cbe109cdcab6c4604c8aa651f70b76 +size 16068890912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..770235e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: pkupie/Llama-3-ProTrix +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/pkupie/Llama-3-ProTrix + + +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-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ProTrix-GGUF/resolve/main/Llama-3-ProTrix.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. + +