commit f78ac25c6e010752948ce83e46b3bf516fac5825 Author: ModelHub XC Date: Tue Jun 2 12:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cupid-Qwen3-4B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d7ad518 --- /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 +Cupid-Qwen3-4B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cupid-Qwen3-4B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cupid-Qwen3-4B-v0.1.IQ4_XS.gguf b/Cupid-Qwen3-4B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..e9355a4 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57bcbe82d0bb390ffacd2c4b831f62950d6ea813170e58b6e985c532bfe735e4 +size 2286316704 diff --git a/Cupid-Qwen3-4B-v0.1.Q2_K.gguf b/Cupid-Qwen3-4B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..10e9b18 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc69a9c114ee152a65d57a4a7454e7b48e70421f0ad4bbe513a7a805a4d5281 +size 1669500064 diff --git a/Cupid-Qwen3-4B-v0.1.Q3_K_L.gguf b/Cupid-Qwen3-4B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..4d908da --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5c4fc9f30f1848801392378742c1c8af4a8ff6f59322b250600155be1f77dc +size 2239786144 diff --git a/Cupid-Qwen3-4B-v0.1.Q3_K_M.gguf b/Cupid-Qwen3-4B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..3600efd --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fde1b113d1486c64e2314b658018119cc3f1978a9d772195f3b359bf8b5dea1 +size 2075618464 diff --git a/Cupid-Qwen3-4B-v0.1.Q3_K_S.gguf b/Cupid-Qwen3-4B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..9e2e757 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4385b5bf8c8fd2787727319c883ecf3b44978af6fe1af952cad45ca2cb5e5f9 +size 1886997664 diff --git a/Cupid-Qwen3-4B-v0.1.Q4_K_M.gguf b/Cupid-Qwen3-4B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..021d81e --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab690d526eb974a7f4b3b9890c0e63619d6eb4cb6defd9788bce77f34337e2cf +size 2497281184 diff --git a/Cupid-Qwen3-4B-v0.1.Q4_K_S.gguf b/Cupid-Qwen3-4B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..25732ec --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4b0518a27cf47a1d23a3ea7422bf07b8dbd6cb935720f6e37c439c3aba0e01 +size 2383309984 diff --git a/Cupid-Qwen3-4B-v0.1.Q5_K_M.gguf b/Cupid-Qwen3-4B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..c021fc4 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59dae5255662b4945a052c7efabc5f5989fa09e16fc81b45cae7ae37474f7c78 +size 2889514144 diff --git a/Cupid-Qwen3-4B-v0.1.Q5_K_S.gguf b/Cupid-Qwen3-4B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..9ae499c --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ebf4c29b7da7622e687ff1ccacc4f7d1891808f648f502d1add4a88337b2ba +size 2823711904 diff --git a/Cupid-Qwen3-4B-v0.1.Q6_K.gguf b/Cupid-Qwen3-4B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..463b080 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5f8de0282bcaba0d2bdc304b8a6c75545327f6a37d9873c5f40be51b9cee89 +size 3306261664 diff --git a/Cupid-Qwen3-4B-v0.1.Q8_0.gguf b/Cupid-Qwen3-4B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..0484928 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:318590b7b762fe25021792270e531fb3334567099b8e99df84d58543071fbd3b +size 4280405664 diff --git a/Cupid-Qwen3-4B-v0.1.f16.gguf b/Cupid-Qwen3-4B-v0.1.f16.gguf new file mode 100644 index 0000000..77d4af4 --- /dev/null +++ b/Cupid-Qwen3-4B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11d9730e7148bf1f4d43ceca5c83594a0750de780f1fdfe208d994cdc81fff7 +size 8051285664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d81ed33 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Torero96Dev/Cupid-Qwen3-4B-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- roleplay +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Torero96Dev/Cupid-Qwen3-4B-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cupid-Qwen3-4B-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-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/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cupid-Qwen3-4B-v0.1-GGUF/resolve/main/Cupid-Qwen3-4B-v0.1.f16.gguf) | f16 | 8.2 | 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. + +