commit 3d7e6ae32468e31b98dfaa14463be93dac2f4657 Author: ModelHub XC Date: Mon Oct 12 11:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aria-7b-128k-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bc7bcd6 --- /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 +Aria-7b-128k-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aria-7b-128k-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aria-7b-128k-v3.IQ4_XS.gguf b/Aria-7b-128k-v3.IQ4_XS.gguf new file mode 100644 index 0000000..58914c0 --- /dev/null +++ b/Aria-7b-128k-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c03b14d1f70ec5d3bbfadda69219605a49e6682e45599ddb1c0ae275fb284959 +size 3944389664 diff --git a/Aria-7b-128k-v3.Q2_K.gguf b/Aria-7b-128k-v3.Q2_K.gguf new file mode 100644 index 0000000..8b6fa0b --- /dev/null +++ b/Aria-7b-128k-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38330e177966b30f61455ce1d53f0eaf9b65bf6e1fc9316b6a6476e50814ce2 +size 2719243296 diff --git a/Aria-7b-128k-v3.Q3_K_L.gguf b/Aria-7b-128k-v3.Q3_K_L.gguf new file mode 100644 index 0000000..ab9aa94 --- /dev/null +++ b/Aria-7b-128k-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc91db3711501ae97ce291a71560bbb3fe3c9eecb5d2a7c1a1373ac0834ca50a +size 3822025760 diff --git a/Aria-7b-128k-v3.Q3_K_M.gguf b/Aria-7b-128k-v3.Q3_K_M.gguf new file mode 100644 index 0000000..ed1f055 --- /dev/null +++ b/Aria-7b-128k-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425d2ef47f20d09da5771308d7df2c6eebb64ed3e2ee0978f31f0926c3be74d7 +size 3518987296 diff --git a/Aria-7b-128k-v3.Q3_K_S.gguf b/Aria-7b-128k-v3.Q3_K_S.gguf new file mode 100644 index 0000000..1d0db3a --- /dev/null +++ b/Aria-7b-128k-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d2b52a3d454e1511d6109e9383ac7c18eb24b3829e8b370eb700c4667aaa7c +size 3164568608 diff --git a/Aria-7b-128k-v3.Q4_K_M.gguf b/Aria-7b-128k-v3.Q4_K_M.gguf new file mode 100644 index 0000000..ae20144 --- /dev/null +++ b/Aria-7b-128k-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3fb81ccbfdcbf736d4f97930a36ad6c60051d49da35ebd33db65a5328684f2 +size 4368440352 diff --git a/Aria-7b-128k-v3.Q4_K_S.gguf b/Aria-7b-128k-v3.Q4_K_S.gguf new file mode 100644 index 0000000..5401768 --- /dev/null +++ b/Aria-7b-128k-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3c11c48af0bc66fed42ad7f5dfacb5a5f0e03b307a7c0f152017d66bbccfe34 +size 4140375072 diff --git a/Aria-7b-128k-v3.Q5_K_M.gguf b/Aria-7b-128k-v3.Q5_K_M.gguf new file mode 100644 index 0000000..11f7218 --- /dev/null +++ b/Aria-7b-128k-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d1495d35ce88076a9d164f3dd66fe4787f6793635027e4b52c1b712a5a802f +size 5131410464 diff --git a/Aria-7b-128k-v3.Q5_K_S.gguf b/Aria-7b-128k-v3.Q5_K_S.gguf new file mode 100644 index 0000000..3b27cb3 --- /dev/null +++ b/Aria-7b-128k-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8271f71c198192303ea36bf919a14eb20ac2328c50a45f5eb171598551a433c +size 4997717024 diff --git a/Aria-7b-128k-v3.Q6_K.gguf b/Aria-7b-128k-v3.Q6_K.gguf new file mode 100644 index 0000000..d05a4d4 --- /dev/null +++ b/Aria-7b-128k-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ee134170083ae616863bc04d5666880a7ed08a923df42ba470b68416766ccd +size 5942066208 diff --git a/Aria-7b-128k-v3.Q8_0.gguf b/Aria-7b-128k-v3.Q8_0.gguf new file mode 100644 index 0000000..7cc9bb5 --- /dev/null +++ b/Aria-7b-128k-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d073f03bff504af1437422f0d6d1fbce25cd8b891a2b4e539d40748ac42b3f8 +size 7695858720 diff --git a/Aria-7b-128k-v3.f16.gguf b/Aria-7b-128k-v3.f16.gguf new file mode 100644 index 0000000..b6361de --- /dev/null +++ b/Aria-7b-128k-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a997141108b3769c3ab19cd0e28e1ffcbdce27d7bec2c40bc4c15bb969c2a7 +size 14484732960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00f3e62 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Jebadiah/Aria-7b-128k-v3 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Jebadiah/Aria-7b-128k-v3 + + +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/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aria-7b-128k-v3-GGUF/resolve/main/Aria-7b-128k-v3.f16.gguf) | f16 | 14.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +