commit 5a0bb01439c8d2593997f0995fbdcbc057966691 Author: ModelHub XC Date: Thu Jun 18 08:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-deepspeed-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8ebe947 --- /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-deepspeed-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-deepspeed-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc49371 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: richard-park/llama3-deepspeed-v1.0 +language: +- ko +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/richard-park/llama3-deepspeed-v1.0 + + +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-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-deepspeed-v1.0-GGUF/resolve/main/llama3-deepspeed-v1.0.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-deepspeed-v1.0.IQ3_M.gguf b/llama3-deepspeed-v1.0.IQ3_M.gguf new file mode 100644 index 0000000..b95e7ea --- /dev/null +++ b/llama3-deepspeed-v1.0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a7ec20a374fb8fbf8c23a2856a08504d84865d51af7102450a5e3ff0e95cbe +size 3784823584 diff --git a/llama3-deepspeed-v1.0.IQ3_S.gguf b/llama3-deepspeed-v1.0.IQ3_S.gguf new file mode 100644 index 0000000..ee8fb4f --- /dev/null +++ b/llama3-deepspeed-v1.0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fe374154ba87a320f48ca2762e2d5a048ee5959688961a326ca6568dae6d93 +size 3682325280 diff --git a/llama3-deepspeed-v1.0.IQ3_XS.gguf b/llama3-deepspeed-v1.0.IQ3_XS.gguf new file mode 100644 index 0000000..f117163 --- /dev/null +++ b/llama3-deepspeed-v1.0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6645d2b3652154a13c498433c7862ffc33f144fa6c2fee2a136403d159261d +size 3518747424 diff --git a/llama3-deepspeed-v1.0.IQ4_XS.gguf b/llama3-deepspeed-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..d9b78b3 --- /dev/null +++ b/llama3-deepspeed-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970415f7a9d9fb19f77976401bf77013e1af4fa6e358ce619dd3d48cf22df090 +size 4484363040 diff --git a/llama3-deepspeed-v1.0.Q2_K.gguf b/llama3-deepspeed-v1.0.Q2_K.gguf new file mode 100644 index 0000000..e3b8b41 --- /dev/null +++ b/llama3-deepspeed-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3de547407647292c115a5b6bd079b27dc399f0852b83390f02302c22fc3b243 +size 3179131680 diff --git a/llama3-deepspeed-v1.0.Q3_K_L.gguf b/llama3-deepspeed-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..315b0da --- /dev/null +++ b/llama3-deepspeed-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150ea452fd67de54ec59752ec4cb80bc7810537c58effb1a9d9793e74f0065fb +size 4321956640 diff --git a/llama3-deepspeed-v1.0.Q3_K_M.gguf b/llama3-deepspeed-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..8c275ff --- /dev/null +++ b/llama3-deepspeed-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177586bf8cbc026f198f3c1660b8d1201577e70f42d07b3b01193d35a3fcfabd +size 4018918176 diff --git a/llama3-deepspeed-v1.0.Q3_K_S.gguf b/llama3-deepspeed-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..23bd578 --- /dev/null +++ b/llama3-deepspeed-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b443a5d8dea1f21e7ba0f5724f15c30e01bbecc73bd32f72df82d6529790d260 +size 3664499488 diff --git a/llama3-deepspeed-v1.0.Q4_K_M.gguf b/llama3-deepspeed-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..0aa20a6 --- /dev/null +++ b/llama3-deepspeed-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b631c0492f727443415e8ef4f9f7d5a9c56929f9116b0e525589ca7d66fb6db7 +size 4920734496 diff --git a/llama3-deepspeed-v1.0.Q4_K_S.gguf b/llama3-deepspeed-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..9855221 --- /dev/null +++ b/llama3-deepspeed-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27924ad725ceeed70c9ad9be8101e40831a8f63e1e41fb43c7e000e8adc0b58c +size 4692669216 diff --git a/llama3-deepspeed-v1.0.Q5_K_M.gguf b/llama3-deepspeed-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..e915ef0 --- /dev/null +++ b/llama3-deepspeed-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c914ff036e379b7f2cd5518e035cda2ec0af88b544efc9fbeba37e2af1830421 +size 5732987680 diff --git a/llama3-deepspeed-v1.0.Q5_K_S.gguf b/llama3-deepspeed-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..1e6068a --- /dev/null +++ b/llama3-deepspeed-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82d0b8ad4aa286bb5363774fd59c2483dd4d5392507a7c8c2c71d80a3bd4628 +size 5599294240 diff --git a/llama3-deepspeed-v1.0.Q6_K.gguf b/llama3-deepspeed-v1.0.Q6_K.gguf new file mode 100644 index 0000000..88bab6d --- /dev/null +++ b/llama3-deepspeed-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6679657ce713ca699682dac77b927a2180c354220966992337a1cea29a2f0ea +size 6596006688 diff --git a/llama3-deepspeed-v1.0.Q8_0.gguf b/llama3-deepspeed-v1.0.Q8_0.gguf new file mode 100644 index 0000000..3dca47f --- /dev/null +++ b/llama3-deepspeed-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1339043c8ca510c9631e1d882a14431610c4f2bb7155cb3a3ecf634fe9ef2158 +size 8540771104 diff --git a/llama3-deepspeed-v1.0.f16.gguf b/llama3-deepspeed-v1.0.f16.gguf new file mode 100644 index 0000000..fb11374 --- /dev/null +++ b/llama3-deepspeed-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d51d4908f887c38188a9a63fa8ad15a9cb2c453eb5deaa785932311c845cbc +size 16068891424