commit 4e8b13bf99650f10939523dadf31069bb488104b Author: ModelHub XC Date: Mon Sep 7 18:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Guru-Llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2fc8a2f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Guru-Llama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Guru-Llama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Guru-Llama-3-8B.IQ4_XS.gguf b/Guru-Llama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ef89e2d --- /dev/null +++ b/Guru-Llama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f85963a58ea5f32f6b900f0b121456aa1d3c00f87de2dde318848b8dadec01 +size 4484363392 diff --git a/Guru-Llama-3-8B.Q2_K.gguf b/Guru-Llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..d82f615 --- /dev/null +++ b/Guru-Llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da446a00ea7ce6d74771c42813e9dfaf9d3cfed35f469094197869d8a914d1e9 +size 3179132032 diff --git a/Guru-Llama-3-8B.Q3_K_L.gguf b/Guru-Llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..ab8910f --- /dev/null +++ b/Guru-Llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64495af414e30c00928a5d60fc24ab7749a44a40a1d8fd8c3e0ca93edf48664f +size 4321956992 diff --git a/Guru-Llama-3-8B.Q3_K_M.gguf b/Guru-Llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..da73f4c --- /dev/null +++ b/Guru-Llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65555f3d12fa8bbba6cb38f7c5857572a5ceb84444dc52f1810990bda6c21023 +size 4018918528 diff --git a/Guru-Llama-3-8B.Q3_K_S.gguf b/Guru-Llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..82d24f9 --- /dev/null +++ b/Guru-Llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136a0d352afe74123a8e98f593ac141892eeadb9febf8663abaa6be5942ce0e1 +size 3664499840 diff --git a/Guru-Llama-3-8B.Q4_K_M.gguf b/Guru-Llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..44bab63 --- /dev/null +++ b/Guru-Llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc0f054e40add169dab4c7aa620aee36aea7eaffeb0cd7eff5a603b7e39dabb0 +size 4920734848 diff --git a/Guru-Llama-3-8B.Q4_K_S.gguf b/Guru-Llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..38c1baa --- /dev/null +++ b/Guru-Llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b744d6e691c3264fca69c15acbfada33a493cd981a68863f50313858f096a25 +size 4692669568 diff --git a/Guru-Llama-3-8B.Q5_K_M.gguf b/Guru-Llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..b37d425 --- /dev/null +++ b/Guru-Llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9e8652b15633b95c3d3e2cfe57d9779a393d06a6194cd32c9b319c342ecee6 +size 5732988032 diff --git a/Guru-Llama-3-8B.Q5_K_S.gguf b/Guru-Llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..d03695a --- /dev/null +++ b/Guru-Llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b4543a9d1069f185439852ec40f9315fe26c1c08c4a0b2b2bae6a741a0f8ff +size 5599294592 diff --git a/Guru-Llama-3-8B.Q6_K.gguf b/Guru-Llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..a9293f7 --- /dev/null +++ b/Guru-Llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c478ca9ff94b041413f2d43378db1412e16b8b6a30d1a62c02f5f4ba4709501e +size 6596007040 diff --git a/Guru-Llama-3-8B.Q8_0.gguf b/Guru-Llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..cb2f9c7 --- /dev/null +++ b/Guru-Llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aa83d520f1bb1af537d6d784b70fec114b335216854432f2ca1d8469b0b4598 +size 8540771456 diff --git a/Guru-Llama-3-8B.f16.gguf b/Guru-Llama-3-8B.f16.gguf new file mode 100644 index 0000000..2408a2e --- /dev/null +++ b/Guru-Llama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71999ce41a1a9a4016b43c3b9efbf1dd1020f49bd55eceb3ca82eaff4dd9cab +size 16068891776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a071460 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: wifibaby4u/Guru-Llama-3-8B +language: +- en +- zh +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- meta +- llama-3 +- llama3中文基座模型 +--- +## About + + + + + + +static quants of https://huggingface.co/wifibaby4u/Guru-Llama-3-8B + + +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/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Guru-Llama-3-8B-GGUF/resolve/main/Guru-Llama-3-8B.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. + +