commit 7430cff9e4d86f9c225012b72b390a8818e52f0b Author: ModelHub XC Date: Mon Sep 28 00:33:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Eden-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..448915a --- /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-Eden.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Eden.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Eden.IQ3_M.gguf b/Llama-3-8B-Eden.IQ3_M.gguf new file mode 100644 index 0000000..ebf25e2 --- /dev/null +++ b/Llama-3-8B-Eden.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59cbbe38087b8715aeaaf91033e9318b558477e085564d13b4c4b772c3722a23 +size 3785336064 diff --git a/Llama-3-8B-Eden.IQ3_S.gguf b/Llama-3-8B-Eden.IQ3_S.gguf new file mode 100644 index 0000000..ad7c4e5 --- /dev/null +++ b/Llama-3-8B-Eden.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e4e53ac7b40a3b5b82f4cf33415d84ed10320ff3588f09a1e656e7f7db40df +size 3682837760 diff --git a/Llama-3-8B-Eden.IQ3_XS.gguf b/Llama-3-8B-Eden.IQ3_XS.gguf new file mode 100644 index 0000000..f7c5893 --- /dev/null +++ b/Llama-3-8B-Eden.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d42e3d9f0ff3446e67edd6d712128f54aaf0a6d98abb56fa0227a5849dec923 +size 3519259904 diff --git a/Llama-3-8B-Eden.IQ4_XS.gguf b/Llama-3-8B-Eden.IQ4_XS.gguf new file mode 100644 index 0000000..65132e5 --- /dev/null +++ b/Llama-3-8B-Eden.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4fc1199792a85b312aff61960c8f64304b54144a2f70f3c9febc627eafa0a19 +size 4484875520 diff --git a/Llama-3-8B-Eden.Q2_K.gguf b/Llama-3-8B-Eden.Q2_K.gguf new file mode 100644 index 0000000..1d891a8 --- /dev/null +++ b/Llama-3-8B-Eden.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c954e146f2e5eb69b74f382f731e42a1afc3d60c4431c4f32f0aa3292cd73bb9 +size 3179644160 diff --git a/Llama-3-8B-Eden.Q3_K_L.gguf b/Llama-3-8B-Eden.Q3_K_L.gguf new file mode 100644 index 0000000..d9dd8f7 --- /dev/null +++ b/Llama-3-8B-Eden.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f0f23ba35968fcde5f77195ce041281828dfe1f32fd9f17a30a8e0fbfb38de4 +size 4322469120 diff --git a/Llama-3-8B-Eden.Q3_K_M.gguf b/Llama-3-8B-Eden.Q3_K_M.gguf new file mode 100644 index 0000000..5054201 --- /dev/null +++ b/Llama-3-8B-Eden.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2a74df248a2a5220ecc3a738bff6f1353eefd4a0838d6a7f3d3025fa5d7249 +size 4019430656 diff --git a/Llama-3-8B-Eden.Q3_K_S.gguf b/Llama-3-8B-Eden.Q3_K_S.gguf new file mode 100644 index 0000000..f89d20d --- /dev/null +++ b/Llama-3-8B-Eden.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e48f3509e9eea02c271f9d5bee07cf0d4bff9610c8facc0aa439e1a0abdb0b +size 3665011968 diff --git a/Llama-3-8B-Eden.Q4_K_M.gguf b/Llama-3-8B-Eden.Q4_K_M.gguf new file mode 100644 index 0000000..d839156 --- /dev/null +++ b/Llama-3-8B-Eden.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a46103942d572fd062001079be7915463d77a7dc83704b3ab00a3577d36e0b +size 4921246976 diff --git a/Llama-3-8B-Eden.Q4_K_S.gguf b/Llama-3-8B-Eden.Q4_K_S.gguf new file mode 100644 index 0000000..4884a34 --- /dev/null +++ b/Llama-3-8B-Eden.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b102feaad78eaa881ee76446529c9cdb0e05a48095dcf180663a6eaa5520bc +size 4693181696 diff --git a/Llama-3-8B-Eden.Q5_K_M.gguf b/Llama-3-8B-Eden.Q5_K_M.gguf new file mode 100644 index 0000000..c6d3516 --- /dev/null +++ b/Llama-3-8B-Eden.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f71903b521e8a1082617a0c14c592254c4d38c7352a4442737b033d70f4b78 +size 5733500160 diff --git a/Llama-3-8B-Eden.Q5_K_S.gguf b/Llama-3-8B-Eden.Q5_K_S.gguf new file mode 100644 index 0000000..55daa7a --- /dev/null +++ b/Llama-3-8B-Eden.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefd1dff256edc29f6d5ac0e3c7f6cab696fc0fbd6f50b6b691da443a16df959 +size 5599806720 diff --git a/Llama-3-8B-Eden.Q6_K.gguf b/Llama-3-8B-Eden.Q6_K.gguf new file mode 100644 index 0000000..1bac10a --- /dev/null +++ b/Llama-3-8B-Eden.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c196fc4685d635641b5b8c13392b21b0c2b8a505a194ba661d418fd418b26617 +size 6596519168 diff --git a/Llama-3-8B-Eden.Q8_0.gguf b/Llama-3-8B-Eden.Q8_0.gguf new file mode 100644 index 0000000..2460262 --- /dev/null +++ b/Llama-3-8B-Eden.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ecf60c28214598bdf879be957df81a66c76f986105f4589f62ec385ef474d2 +size 8541283584 diff --git a/Llama-3-8B-Eden.f16.gguf b/Llama-3-8B-Eden.f16.gguf new file mode 100644 index 0000000..9c6f2a7 --- /dev/null +++ b/Llama-3-8B-Eden.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce3a7a49a05351d24a87f3b1285d4a0aba443c936c458d6ef2230a8160a5ad9 +size 16069403904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de485fc --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Hugosh71/Llama-3-8B-Eden +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + +static quants of https://huggingface.co/Hugosh71/Llama-3-8B-Eden + + +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-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.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. + +