commit 24e94f7dc3ded370483413e797e2507e665e6deb Author: ModelHub XC Date: Sun May 10 05:37:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Alisia-7B-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae20344 --- /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-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Alisia-7B-instruct.IQ4_XS.gguf b/Alisia-7B-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..55dab5b --- /dev/null +++ b/Alisia-7B-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0e1ea476684077d5f9b1df7c558ad067b813c1d378527d8750094658bffdb7 +size 4250296928 diff --git a/Alisia-7B-instruct.Q2_K.gguf b/Alisia-7B-instruct.Q2_K.gguf new file mode 100644 index 0000000..83e802d --- /dev/null +++ b/Alisia-7B-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af7a9f9d6f96da01a991b89d702bb61095b2c5ee64fbfb53e4a3cc43a5a7b04 +size 3015938656 diff --git a/Alisia-7B-instruct.Q3_K_L.gguf b/Alisia-7B-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..3b33dfb --- /dev/null +++ b/Alisia-7B-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e00a65dc6fb2adac847a44c892a8862ae1720a67132346f87b75571dfe2d4b +size 4088457824 diff --git a/Alisia-7B-instruct.Q3_K_M.gguf b/Alisia-7B-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..88e95ac --- /dev/null +++ b/Alisia-7B-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500075f0d3b35b690c56bb429c09c4ff9569b418275a36be315dc77d24420218 +size 3808389728 diff --git a/Alisia-7B-instruct.Q3_K_S.gguf b/Alisia-7B-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..2739e90 --- /dev/null +++ b/Alisia-7B-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f18d4e35a86b16cec766274e500d667e9e35aaa3bb5f867284394a172c7abe7 +size 3492366944 diff --git a/Alisia-7B-instruct.Q4_K_M.gguf b/Alisia-7B-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f95fcc3 --- /dev/null +++ b/Alisia-7B-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:974cf2ff9ef7b05acd71b5e9bf474e9a248178177b91d48a7fceec9032694cb3 +size 4683072096 diff --git a/Alisia-7B-instruct.Q4_K_S.gguf b/Alisia-7B-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..bb56e20 --- /dev/null +++ b/Alisia-7B-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc30c965b13400bcf032375ecd28b0f3862d03c1445797710f928a647b993611 +size 4457767520 diff --git a/Alisia-7B-instruct.Q5_K_M.gguf b/Alisia-7B-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..6bbd35e --- /dev/null +++ b/Alisia-7B-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e9c0ffdd3b194acd5554f5ad141e8776e4c652bfd2edfe30dd16fde6557f196 +size 5444829792 diff --git a/Alisia-7B-instruct.Q5_K_S.gguf b/Alisia-7B-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..1fa17f4 --- /dev/null +++ b/Alisia-7B-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6c75746a3bdff89c9b8617eba5bec776a3e401107215983210ac3b78150805 +size 5315175008 diff --git a/Alisia-7B-instruct.Q6_K.gguf b/Alisia-7B-instruct.Q6_K.gguf new file mode 100644 index 0000000..feb1a80 --- /dev/null +++ b/Alisia-7B-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8c5f4fa2537a195e1176012e6d36c9d1639b62444c01f3e364a50aeecfc8fc +size 6254197344 diff --git a/Alisia-7B-instruct.Q8_0.gguf b/Alisia-7B-instruct.Q8_0.gguf new file mode 100644 index 0000000..abade18 --- /dev/null +++ b/Alisia-7B-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bd5d208c2d44e747766e857773f888af6d702107a65671d8628767cae244da +size 8098523744 diff --git a/Alisia-7B-instruct.f16.gguf b/Alisia-7B-instruct.f16.gguf new file mode 100644 index 0000000..66de2bc --- /dev/null +++ b/Alisia-7B-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342ba37b080cc9ef9949615775c8c38c758f13020b5e951b3fb92c94e5f5e20c +size 15237851744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f92cf39 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Gems234/Alisia-7B-Instruct +language: +- en +- fr +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Gems234/Alisia-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alisia-7B-instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Alisia-7B-instruct-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-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.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. + +