commit beaa9c31abe7a91a7925385815dcc4ade4977002 Author: ModelHub XC Date: Tue May 26 09:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Alisia-7B-Instruct-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7e3c3be --- /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-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alisia-7B-Instruct-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Alisia-7B-Instruct-V1.IQ4_XS.gguf b/Alisia-7B-Instruct-V1.IQ4_XS.gguf new file mode 100644 index 0000000..c1c7541 --- /dev/null +++ b/Alisia-7B-Instruct-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31ff47f91b41e4d4cf89390166afb452719702748f42ef73483a86c8aaae1a2 +size 4250296960 diff --git a/Alisia-7B-Instruct-V1.Q2_K.gguf b/Alisia-7B-Instruct-V1.Q2_K.gguf new file mode 100644 index 0000000..0c7e392 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0390340a249e42f1b46e15c03f7f3f3fb63f9dcd4b7fb4eaaa20b080b23dd70 +size 3015938688 diff --git a/Alisia-7B-Instruct-V1.Q3_K_L.gguf b/Alisia-7B-Instruct-V1.Q3_K_L.gguf new file mode 100644 index 0000000..31739ed --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe93fb9b4f467271661e18cf61087fb965d7ed941b4541a63377d2caae8f5de3 +size 4088457856 diff --git a/Alisia-7B-Instruct-V1.Q3_K_M.gguf b/Alisia-7B-Instruct-V1.Q3_K_M.gguf new file mode 100644 index 0000000..fdeffd8 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7dd0a19230b3e49ec4e4bea961ad384145fc847003900e73a616e0db209ce79 +size 3808389760 diff --git a/Alisia-7B-Instruct-V1.Q3_K_S.gguf b/Alisia-7B-Instruct-V1.Q3_K_S.gguf new file mode 100644 index 0000000..b936474 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5603f287455460691093d251d18ec484a56a333c42dc51ea8b6a4f2a962aab14 +size 3492366976 diff --git a/Alisia-7B-Instruct-V1.Q4_K_M.gguf b/Alisia-7B-Instruct-V1.Q4_K_M.gguf new file mode 100644 index 0000000..c6711c8 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfeab8f986a51fd28c880f9f7dde5b0e3d494e0592ca7f4c21cc7f6e9af9ac80 +size 4683072128 diff --git a/Alisia-7B-Instruct-V1.Q4_K_S.gguf b/Alisia-7B-Instruct-V1.Q4_K_S.gguf new file mode 100644 index 0000000..7e1dba4 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f52dfb6e297bcee983a9dcf0e41107dfcb69629516fee9a902ac19c16ec4b8 +size 4457767552 diff --git a/Alisia-7B-Instruct-V1.Q5_K_M.gguf b/Alisia-7B-Instruct-V1.Q5_K_M.gguf new file mode 100644 index 0000000..110b2bd --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debf9b10a02990c15110a5f6658f25ecbf700501ffb02417a75cf611c2c3d9d7 +size 5444829824 diff --git a/Alisia-7B-Instruct-V1.Q5_K_S.gguf b/Alisia-7B-Instruct-V1.Q5_K_S.gguf new file mode 100644 index 0000000..ea87dd0 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09bf2f52f427b52902c6b171ac6c7e67bfa831f32f0dc595dcba0a605bbdee2e +size 5315175040 diff --git a/Alisia-7B-Instruct-V1.Q6_K.gguf b/Alisia-7B-Instruct-V1.Q6_K.gguf new file mode 100644 index 0000000..6e798a1 --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db751b540c001171e39591a1ec1a688a1f3f1402174419053a0c9bbe628317bd +size 6254197376 diff --git a/Alisia-7B-Instruct-V1.Q8_0.gguf b/Alisia-7B-Instruct-V1.Q8_0.gguf new file mode 100644 index 0000000..d86e17b --- /dev/null +++ b/Alisia-7B-Instruct-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5adc80cc90854d0aa73deeb252d4f4e76012d32a2b750a2dd938168695a343a +size 8098523776 diff --git a/Alisia-7B-Instruct-V1.f16.gguf b/Alisia-7B-Instruct-V1.f16.gguf new file mode 100644 index 0000000..e4aa889 --- /dev/null +++ b/Alisia-7B-Instruct-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155e15a55693a6583c81c57cbde7b7b896dbe977a8ffb23fddeda90b6959962c +size 15237851776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..50770ac --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Gems234/Alisia-7B-Instruct-V1 +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-V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alisia-7B-Instruct-V1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-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-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-Instruct-V1-GGUF/resolve/main/Alisia-7B-Instruct-V1.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. + +