commit fae01cf118c0b6ef4c174b599c1ef186f033cbde Author: ModelHub XC Date: Fri Oct 9 22:21:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-EGO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aae5396 --- /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 +Llama-3-8B-EGO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-EGO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-EGO.IQ4_XS.gguf b/Llama-3-8B-EGO.IQ4_XS.gguf new file mode 100644 index 0000000..dcfb134 --- /dev/null +++ b/Llama-3-8B-EGO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac7ad279d00ac9b60f2def5e4b96a5eeb037a68e3ee588abdd27c4e775a5ced +size 4484363200 diff --git a/Llama-3-8B-EGO.Q2_K.gguf b/Llama-3-8B-EGO.Q2_K.gguf new file mode 100644 index 0000000..16840c1 --- /dev/null +++ b/Llama-3-8B-EGO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54df871b84f250f24a5f2b8c37c8013cb3cebc62314178fcc4d9629b30ba2666 +size 3179131840 diff --git a/Llama-3-8B-EGO.Q3_K_L.gguf b/Llama-3-8B-EGO.Q3_K_L.gguf new file mode 100644 index 0000000..3822c75 --- /dev/null +++ b/Llama-3-8B-EGO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6be09ef295acaecdb427f343299d6c964c73dae9cc7fc14350a151c1bc94a32 +size 4321956800 diff --git a/Llama-3-8B-EGO.Q3_K_M.gguf b/Llama-3-8B-EGO.Q3_K_M.gguf new file mode 100644 index 0000000..7bac5e4 --- /dev/null +++ b/Llama-3-8B-EGO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634d06270224b717012a86c960ca22e12fc8123192be3b8d7d7dfe507250ad72 +size 4018918336 diff --git a/Llama-3-8B-EGO.Q3_K_S.gguf b/Llama-3-8B-EGO.Q3_K_S.gguf new file mode 100644 index 0000000..e519b92 --- /dev/null +++ b/Llama-3-8B-EGO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56daa795612d62a563583504db65f75c8473f7d33e8189322051e380db482e45 +size 3664499648 diff --git a/Llama-3-8B-EGO.Q4_K_M.gguf b/Llama-3-8B-EGO.Q4_K_M.gguf new file mode 100644 index 0000000..d9cde4d --- /dev/null +++ b/Llama-3-8B-EGO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3373b69da69a792b47c955ccd5151b9c2aa416b75f5991a7c4ca6cf0e0a13643 +size 4920734656 diff --git a/Llama-3-8B-EGO.Q4_K_S.gguf b/Llama-3-8B-EGO.Q4_K_S.gguf new file mode 100644 index 0000000..b9b5468 --- /dev/null +++ b/Llama-3-8B-EGO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ebfa57d38c969d7ad28fdb56ad2755a46444855ea0f20879229d0fd26fcb34a +size 4692669376 diff --git a/Llama-3-8B-EGO.Q5_K_M.gguf b/Llama-3-8B-EGO.Q5_K_M.gguf new file mode 100644 index 0000000..54c25fb --- /dev/null +++ b/Llama-3-8B-EGO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2085eb1d67f24f442fc4165120587ad644c508872eeeed8d6d085b18c52cd2ef +size 5732987840 diff --git a/Llama-3-8B-EGO.Q5_K_S.gguf b/Llama-3-8B-EGO.Q5_K_S.gguf new file mode 100644 index 0000000..5f44171 --- /dev/null +++ b/Llama-3-8B-EGO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90935d8123774e38e6c56cedb93d54fbc4c5b65c589d858588ffd43e7ecb3ec6 +size 5599294400 diff --git a/Llama-3-8B-EGO.Q6_K.gguf b/Llama-3-8B-EGO.Q6_K.gguf new file mode 100644 index 0000000..c4bf553 --- /dev/null +++ b/Llama-3-8B-EGO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a0e387b470de3135358ccb6042d75d5b88245e542b4765a82092fca7169703 +size 6596006848 diff --git a/Llama-3-8B-EGO.Q8_0.gguf b/Llama-3-8B-EGO.Q8_0.gguf new file mode 100644 index 0000000..7ff73e2 --- /dev/null +++ b/Llama-3-8B-EGO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d442e003f9d7d4d9ce7a54b7b270a5cff163b15147c80ccdcaff47752726c6 +size 8540771264 diff --git a/Llama-3-8B-EGO.f16.gguf b/Llama-3-8B-EGO.f16.gguf new file mode 100644 index 0000000..f362efb --- /dev/null +++ b/Llama-3-8B-EGO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2857650006c2ecb3ece7ae3aa5b25d08e1a5bee1cbd1011ef6bd9204f665f6 +size 16068891584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc66682 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Envoid/Llama-3-8B-EGO +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/Envoid/Llama-3-8B-EGO + + +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-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-EGO-GGUF/resolve/main/Llama-3-8B-EGO.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. + +