commit fdac98d76cf23ce27d3e0ad1669c560af191c79b Author: ModelHub XC Date: Wed Jun 10 09:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Veiled-Calla-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a541e6f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Veiled-Calla-4B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Veiled-Calla-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a44e4a6 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: soob3123/Veiled-Calla-4B +datasets: +- soob3123/rp_dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- roleplay +- creative-writing +- immersive +- mystery +- storytelling +--- +## About + + + + + + +static quants of https://huggingface.co/soob3123/Veiled-Calla-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Veiled-Calla-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Veiled-Calla-4B-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/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Veiled-Calla-4B-GGUF/resolve/main/Veiled-Calla-4B.f16.gguf) | f16 | 7.9 | 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. + + diff --git a/Veiled-Calla-4B.IQ4_XS.gguf b/Veiled-Calla-4B.IQ4_XS.gguf new file mode 100644 index 0000000..ce6ba85 --- /dev/null +++ b/Veiled-Calla-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8f21e782086b14c60ddf92f6be2c40e3d937a32abd701c63da4bcb4ee8998b +size 2279626400 diff --git a/Veiled-Calla-4B.Q2_K.gguf b/Veiled-Calla-4B.Q2_K.gguf new file mode 100644 index 0000000..71c9e92 --- /dev/null +++ b/Veiled-Calla-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc459f4e6a9191be31701546132c688e147ea6ed062fc0a18c915ae9ab01f85 +size 1729164960 diff --git a/Veiled-Calla-4B.Q3_K_L.gguf b/Veiled-Calla-4B.Q3_K_L.gguf new file mode 100644 index 0000000..52304f3 --- /dev/null +++ b/Veiled-Calla-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d6fa7f6d5a5a03855ff5cf0d2665ef8cf877e9cb370b284ca0b917f334cdfe +size 2236085920 diff --git a/Veiled-Calla-4B.Q3_K_M.gguf b/Veiled-Calla-4B.Q3_K_M.gguf new file mode 100644 index 0000000..32fbd5a --- /dev/null +++ b/Veiled-Calla-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e063c55eeb7f35983bb5b2e7e13f3c71e0d2e3a1a38af0dc9cf2687f9d7c2ec +size 2098460320 diff --git a/Veiled-Calla-4B.Q3_K_S.gguf b/Veiled-Calla-4B.Q3_K_S.gguf new file mode 100644 index 0000000..6cdd0ca --- /dev/null +++ b/Veiled-Calla-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b7aa09b5cd8066123e8c10c56f38850bb9a563088e3df1650127701de3247a +size 1937364640 diff --git a/Veiled-Calla-4B.Q4_K_M.gguf b/Veiled-Calla-4B.Q4_K_M.gguf new file mode 100644 index 0000000..24eda45 --- /dev/null +++ b/Veiled-Calla-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273ff2c42fba8e804e0a0022ec6d82835c3925c302f58859be4e7c3654b97a97 +size 2489894560 diff --git a/Veiled-Calla-4B.Q4_K_S.gguf b/Veiled-Calla-4B.Q4_K_S.gguf new file mode 100644 index 0000000..b36e74c --- /dev/null +++ b/Veiled-Calla-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073e1ea30d448f44a5b5d9fb1cd057304736bb9e6b4d419041f5d8a331a34ed2 +size 2377930400 diff --git a/Veiled-Calla-4B.Q5_K_M.gguf b/Veiled-Calla-4B.Q5_K_M.gguf new file mode 100644 index 0000000..4852ac7 --- /dev/null +++ b/Veiled-Calla-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28d3896f84aad32411073d9e591c8a32e0c327dcfa114f129540700b4b67346 +size 2829698720 diff --git a/Veiled-Calla-4B.Q5_K_S.gguf b/Veiled-Calla-4B.Q5_K_S.gguf new file mode 100644 index 0000000..5a7e3f4 --- /dev/null +++ b/Veiled-Calla-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64157170ea3c557a928d3815f130d563a1f9624033d7b09813dfe4e19c72a26e +size 2764592800 diff --git a/Veiled-Calla-4B.Q6_K.gguf b/Veiled-Calla-4B.Q6_K.gguf new file mode 100644 index 0000000..7a29ca0 --- /dev/null +++ b/Veiled-Calla-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47746d37a32445a1afc28567bdc14fdc50e20660f4a617c092cb13434f3e6137 +size 3190740640 diff --git a/Veiled-Calla-4B.Q8_0.gguf b/Veiled-Calla-4B.Q8_0.gguf new file mode 100644 index 0000000..3f57300 --- /dev/null +++ b/Veiled-Calla-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fdae2816dc2876640179be30834cb6c147ed64b5d7598841c0ea84d9bdff22 +size 4130402720 diff --git a/Veiled-Calla-4B.f16.gguf b/Veiled-Calla-4B.f16.gguf new file mode 100644 index 0000000..b9ef864 --- /dev/null +++ b/Veiled-Calla-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f3d1a5b1e4392348b3ea7a1dc5ea6ef0a5e33c2c8f5ad96c6d3c7752809520 +size 7767804320 diff --git a/Veiled-Calla-4B.mmproj-Q8_0.gguf b/Veiled-Calla-4B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..cce9225 --- /dev/null +++ b/Veiled-Calla-4B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b32907e4e7ef4ab8d29da6444f3033b27a242a772db7136fdc3e4d9195edc3 +size 588612384 diff --git a/Veiled-Calla-4B.mmproj-f16.gguf b/Veiled-Calla-4B.mmproj-f16.gguf new file mode 100644 index 0000000..3be244e --- /dev/null +++ b/Veiled-Calla-4B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c0fb064b019a6972856aaae2c7e4792858af3ca4561be2dbf649123ba6c40cb +size 851251104