commit 1fc10269199fe582bc78f3cccf4c4387f00904b1 Author: ModelHub XC Date: Mon Apr 27 15:19:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aura-llama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d35d7d5 --- /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 +Aura-llama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.f16.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-llama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aura-llama.IQ4_XS.gguf b/Aura-llama.IQ4_XS.gguf new file mode 100644 index 0000000..830c5d9 --- /dev/null +++ b/Aura-llama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3180710856bb64acc58f97706cac43da88758f62f71562a854c246dd2de2a970 +size 5892214400 diff --git a/Aura-llama.Q2_K.gguf b/Aura-llama.Q2_K.gguf new file mode 100644 index 0000000..69930ee --- /dev/null +++ b/Aura-llama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250af53110f1fea2d8fff211448cb3ceb0613db83505f938c92c7119a6db329a +size 4142124672 diff --git a/Aura-llama.Q3_K_L.gguf b/Aura-llama.Q3_K_L.gguf new file mode 100644 index 0000000..f81299e --- /dev/null +++ b/Aura-llama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9be7d78b55f858ae22e77770dd98542731be573a862e2e3e3e7a850bdb014dd +size 5693501056 diff --git a/Aura-llama.Q3_K_M.gguf b/Aura-llama.Q3_K_M.gguf new file mode 100644 index 0000000..6485890 --- /dev/null +++ b/Aura-llama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314259c86fa0d3822e8210889bc809a2600fbaca129ee7dbfd0e8c793af20aad +size 5270924928 diff --git a/Aura-llama.Q3_K_S.gguf b/Aura-llama.Q3_K_S.gguf new file mode 100644 index 0000000..61398da --- /dev/null +++ b/Aura-llama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba0ec9433e0c4002de298877885435b9fb1ae2be9279857ad5274295be74b20 +size 4789497472 diff --git a/Aura-llama.Q4_K_M.gguf b/Aura-llama.Q4_K_M.gguf new file mode 100644 index 0000000..cb51583 --- /dev/null +++ b/Aura-llama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf2c29c4f75f10393f55ea7aa69589a5fa468cc95456d75c9c444e140ca2ff9 +size 6490656384 diff --git a/Aura-llama.Q4_K_S.gguf b/Aura-llama.Q4_K_S.gguf new file mode 100644 index 0000000..49c10a5 --- /dev/null +++ b/Aura-llama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b20935fe192352cbd0fdea181b2ddcabe2dac1b7acf2990ef5e7b69e34ff62 +size 6172610176 diff --git a/Aura-llama.Q5_K_M.gguf b/Aura-llama.Q5_K_M.gguf new file mode 100644 index 0000000..383bf46 --- /dev/null +++ b/Aura-llama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843f87b2fd2fccf6e684d4788698872bd43e4f9eda778a4190a181a1ca7b4631 +size 7582879360 diff --git a/Aura-llama.Q5_K_S.gguf b/Aura-llama.Q5_K_S.gguf new file mode 100644 index 0000000..b3f0797 --- /dev/null +++ b/Aura-llama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b7bf2a3533e637c70976888c0a0bc39820225d44c667f8d485f9c2bfda2c0f +size 7399050880 diff --git a/Aura-llama.Q6_K.gguf b/Aura-llama.Q6_K.gguf new file mode 100644 index 0000000..7d55c70 --- /dev/null +++ b/Aura-llama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7a683113aaae3e52d8b0b22e02daa682c8d0871321e88105b1b55cb499189b +size 8743366272 diff --git a/Aura-llama.Q8_0.gguf b/Aura-llama.Q8_0.gguf new file mode 100644 index 0000000..52bdd16 --- /dev/null +++ b/Aura-llama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3deea135423574f0bb4e1ae27d9e5d659554f8420e71e0258431ee966708af05 +size 11321994880 diff --git a/Aura-llama.f16.gguf b/Aura-llama.f16.gguf new file mode 100644 index 0000000..a6928f6 --- /dev/null +++ b/Aura-llama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3bda35aa0f442f77ff765af9f9f7c0f220a8fb9043f1ac440e4867e3fcb4e6 +size 21303783040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..16ba284 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: SteelStorage/Aura-llama +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- NousResearch/Meta-Llama-3-8B-Instruct +--- +## About + + + + + + +static quants of https://huggingface.co/SteelStorage/Aura-llama + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aura-llama-i1-GGUF +## 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/Aura-llama-GGUF/resolve/main/Aura-llama.Q2_K.gguf) | Q2_K | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q3_K_S.gguf) | Q3_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q3_K_M.gguf) | Q3_K_M | 5.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q3_K_L.gguf) | Q3_K_L | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.IQ4_XS.gguf) | IQ4_XS | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q4_K_S.gguf) | Q4_K_S | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q5_K_S.gguf) | Q5_K_S | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q5_K_M.gguf) | Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q6_K.gguf) | Q6_K | 8.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.Q8_0.gguf) | Q8_0 | 11.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-llama-GGUF/resolve/main/Aura-llama.f16.gguf) | f16 | 21.4 | 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. + +