commit e593accdaae04c62d01c3da2531cd22006a6295c Author: ModelHub XC Date: Mon Jul 6 23:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Alisia-7B-v0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a94fc7e --- /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 +Alisia-7B-v0.f16.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-v0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Alisia-7B-v0.IQ4_XS.gguf b/Alisia-7B-v0.IQ4_XS.gguf new file mode 100644 index 0000000..b6cbe68 --- /dev/null +++ b/Alisia-7B-v0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba576c9c15f718f255e6df8f7744301c899dcc0b541b68f9f82f184a926526a8 +size 4250296704 diff --git a/Alisia-7B-v0.Q2_K.gguf b/Alisia-7B-v0.Q2_K.gguf new file mode 100644 index 0000000..53355ca --- /dev/null +++ b/Alisia-7B-v0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69635e75a6e935961757da10b7770a8abea134e5601bff785c6d8f447e0141b5 +size 3015938432 diff --git a/Alisia-7B-v0.Q3_K_L.gguf b/Alisia-7B-v0.Q3_K_L.gguf new file mode 100644 index 0000000..fb9d9b0 --- /dev/null +++ b/Alisia-7B-v0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a8824c515ce6cb2b4f99a6eb701fbd89ca8a635f8444a5483b56fb9c305537 +size 4088457600 diff --git a/Alisia-7B-v0.Q3_K_M.gguf b/Alisia-7B-v0.Q3_K_M.gguf new file mode 100644 index 0000000..6308947 --- /dev/null +++ b/Alisia-7B-v0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4045c19d218bf763b548af8d0b5e9a6e70763202d531e06ac7c1e5f0fd01bd2 +size 3808389504 diff --git a/Alisia-7B-v0.Q3_K_S.gguf b/Alisia-7B-v0.Q3_K_S.gguf new file mode 100644 index 0000000..292424b --- /dev/null +++ b/Alisia-7B-v0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b406c8041207f0fcb02a46ffeb78735c1481963d54d6ecd4d8357b07d570973 +size 3492366720 diff --git a/Alisia-7B-v0.Q4_K_M.gguf b/Alisia-7B-v0.Q4_K_M.gguf new file mode 100644 index 0000000..551e23c --- /dev/null +++ b/Alisia-7B-v0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d647bd81c80cef9aedd38aef8f3649b1cc24e3ff1aafe84509dad3847541d458 +size 4683071872 diff --git a/Alisia-7B-v0.Q4_K_S.gguf b/Alisia-7B-v0.Q4_K_S.gguf new file mode 100644 index 0000000..bf8f52a --- /dev/null +++ b/Alisia-7B-v0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63556b373a7ffc702f071e41c13d18e62730f80e8e5c17b8f85e8a68211311b0 +size 4457767296 diff --git a/Alisia-7B-v0.Q5_K_M.gguf b/Alisia-7B-v0.Q5_K_M.gguf new file mode 100644 index 0000000..212010c --- /dev/null +++ b/Alisia-7B-v0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0cd12a98e3d66373e76b6e72b1662983a76ac6b7f1001f784b93de11db20e5 +size 5444829568 diff --git a/Alisia-7B-v0.Q5_K_S.gguf b/Alisia-7B-v0.Q5_K_S.gguf new file mode 100644 index 0000000..5fc9385 --- /dev/null +++ b/Alisia-7B-v0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142b2bb3ca18905fb6233981e42952b43d8457839f8ff3f636cb251a986020a5 +size 5315174784 diff --git a/Alisia-7B-v0.Q6_K.gguf b/Alisia-7B-v0.Q6_K.gguf new file mode 100644 index 0000000..9c3ddac --- /dev/null +++ b/Alisia-7B-v0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47eb685f4dbf87cb5f8c8282d39edc18367187e25a399202eda4146158cba224 +size 6254197120 diff --git a/Alisia-7B-v0.Q8_0.gguf b/Alisia-7B-v0.Q8_0.gguf new file mode 100644 index 0000000..1c042f6 --- /dev/null +++ b/Alisia-7B-v0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59f6596ca96131d448ad4fc7903fcf3b140ea8a3d68e0749d807297279a4a14 +size 8098523520 diff --git a/Alisia-7B-v0.f16.gguf b/Alisia-7B-v0.f16.gguf new file mode 100644 index 0000000..d4b1a59 --- /dev/null +++ b/Alisia-7B-v0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7247c30d15367d38d50e0c9517de894cf4793b4913fa4d4106f0480653ac14 +size 15237851520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4a5005c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: alisia-ai/Alisia-7B-v0 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/alisia-ai/Alisia-7B-v0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alisia-7B-v0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Alisia-7B-v0-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/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-v0-GGUF/resolve/main/Alisia-7B-v0.f16.gguf) | f16 | 15.3 | 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. + +