From 93deebbcdf16497e45a090dce2e1d792e13c91a8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 2 Jun 2026 12:55:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/DeepAttriCap-VLA-3B-GGUF Source: Original Platform --- .gitattributes | 49 ++++++++++++++++ DeepAttriCap-VLA-3B.IQ4_XS.gguf | 3 + DeepAttriCap-VLA-3B.Q2_K.gguf | 3 + DeepAttriCap-VLA-3B.Q3_K_L.gguf | 3 + DeepAttriCap-VLA-3B.Q3_K_M.gguf | 3 + DeepAttriCap-VLA-3B.Q3_K_S.gguf | 3 + DeepAttriCap-VLA-3B.Q4_K_M.gguf | 3 + DeepAttriCap-VLA-3B.Q4_K_S.gguf | 3 + DeepAttriCap-VLA-3B.Q5_K_M.gguf | 3 + DeepAttriCap-VLA-3B.Q5_K_S.gguf | 3 + DeepAttriCap-VLA-3B.Q6_K.gguf | 3 + DeepAttriCap-VLA-3B.Q8_0.gguf | 3 + DeepAttriCap-VLA-3B.f16.gguf | 3 + DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf | 3 + DeepAttriCap-VLA-3B.mmproj-f16.gguf | 3 + README.md | 85 ++++++++++++++++++++++++++++ 16 files changed, 176 insertions(+) create mode 100644 .gitattributes create mode 100644 DeepAttriCap-VLA-3B.IQ4_XS.gguf create mode 100644 DeepAttriCap-VLA-3B.Q2_K.gguf create mode 100644 DeepAttriCap-VLA-3B.Q3_K_L.gguf create mode 100644 DeepAttriCap-VLA-3B.Q3_K_M.gguf create mode 100644 DeepAttriCap-VLA-3B.Q3_K_S.gguf create mode 100644 DeepAttriCap-VLA-3B.Q4_K_M.gguf create mode 100644 DeepAttriCap-VLA-3B.Q4_K_S.gguf create mode 100644 DeepAttriCap-VLA-3B.Q5_K_M.gguf create mode 100644 DeepAttriCap-VLA-3B.Q5_K_S.gguf create mode 100644 DeepAttriCap-VLA-3B.Q6_K.gguf create mode 100644 DeepAttriCap-VLA-3B.Q8_0.gguf create mode 100644 DeepAttriCap-VLA-3B.f16.gguf create mode 100644 DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf create mode 100644 DeepAttriCap-VLA-3B.mmproj-f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..314ecf6 --- /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 +DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepAttriCap-VLA-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepAttriCap-VLA-3B.IQ4_XS.gguf b/DeepAttriCap-VLA-3B.IQ4_XS.gguf new file mode 100644 index 0000000..7aa0146 --- /dev/null +++ b/DeepAttriCap-VLA-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc3b085ae0fbb0a17b1d574ef40fe224c0a6ea3be80cdd8b32678298b609516 +size 1753185312 diff --git a/DeepAttriCap-VLA-3B.Q2_K.gguf b/DeepAttriCap-VLA-3B.Q2_K.gguf new file mode 100644 index 0000000..c1ad0dd --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae3043dddb289b7d73973e584001c2945b9639f61dc1a9cbce3fc8a181c8c6b +size 1274756128 diff --git a/DeepAttriCap-VLA-3B.Q3_K_L.gguf b/DeepAttriCap-VLA-3B.Q3_K_L.gguf new file mode 100644 index 0000000..485b0b7 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d440a8091ef925523840207356d8484f2dc3cfac9d96e579f444486fdac822a +size 1707392032 diff --git a/DeepAttriCap-VLA-3B.Q3_K_M.gguf b/DeepAttriCap-VLA-3B.Q3_K_M.gguf new file mode 100644 index 0000000..312ebf6 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e36bdab29e153a12a71c442748cb46afbd62314f2008ac20e50e2db7be93fc +size 1590475808 diff --git a/DeepAttriCap-VLA-3B.Q3_K_S.gguf b/DeepAttriCap-VLA-3B.Q3_K_S.gguf new file mode 100644 index 0000000..2bbf8be --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561a3c22ba726bb1ee34b43461f1d3f02ebe5730c727c0f74020099661251cf2 +size 1454357536 diff --git a/DeepAttriCap-VLA-3B.Q4_K_M.gguf b/DeepAttriCap-VLA-3B.Q4_K_M.gguf new file mode 100644 index 0000000..0f62529 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b081ee0a3e04011600010380235b307ec2f08a49e3e7fc54bd46ec731a51c8c0 +size 1929903136 diff --git a/DeepAttriCap-VLA-3B.Q4_K_S.gguf b/DeepAttriCap-VLA-3B.Q4_K_S.gguf new file mode 100644 index 0000000..d66f6f8 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9730d8fa3e5dcb55a177a9dff5bbe05602eb70426b95f80ec6690afb1ec9cc +size 1834384416 diff --git a/DeepAttriCap-VLA-3B.Q5_K_M.gguf b/DeepAttriCap-VLA-3B.Q5_K_M.gguf new file mode 100644 index 0000000..6ff1aa1 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c864f1e30cf16210dd6af274b1aadddc25ebe9e672ecf8443f72ba6588741486 +size 2224815136 diff --git a/DeepAttriCap-VLA-3B.Q5_K_S.gguf b/DeepAttriCap-VLA-3B.Q5_K_S.gguf new file mode 100644 index 0000000..c1595a0 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b360986791e768f7d2dff1c2e287758e0c2f8f8aa16e9c9277b8d79d08075690 +size 2169666592 diff --git a/DeepAttriCap-VLA-3B.Q6_K.gguf b/DeepAttriCap-VLA-3B.Q6_K.gguf new file mode 100644 index 0000000..3a41a07 --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311a3ddc5d2225937a260b0bbda27d53d06ab5bba63f08cd761c990b7846f89c +size 2538159136 diff --git a/DeepAttriCap-VLA-3B.Q8_0.gguf b/DeepAttriCap-VLA-3B.Q8_0.gguf new file mode 100644 index 0000000..ebcc6ee --- /dev/null +++ b/DeepAttriCap-VLA-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2dc070e54f618f73ba8928f0eef78d33c9ced1e97acfb2b5485f6837ef2c89 +size 3285476384 diff --git a/DeepAttriCap-VLA-3B.f16.gguf b/DeepAttriCap-VLA-3B.f16.gguf new file mode 100644 index 0000000..7cefc3d --- /dev/null +++ b/DeepAttriCap-VLA-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f47c3b4b895ec9f4f70aa681ce0a11506cf43b8238c56440591cc75907d084e +size 6178317344 diff --git a/DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf b/DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..bcd05b2 --- /dev/null +++ b/DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1676e49e26a4be2a22e2b2b82304ef3018b9be3c810d123f7caa68b6826f6713 +size 847769952 diff --git a/DeepAttriCap-VLA-3B.mmproj-f16.gguf b/DeepAttriCap-VLA-3B.mmproj-f16.gguf new file mode 100644 index 0000000..5fa99e3 --- /dev/null +++ b/DeepAttriCap-VLA-3B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f2e6a442daeb07d6ea0ef399abca3095bf5e978ae4f6ad37e84ad4fb9b5809 +size 1338429792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..053e5d7 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: prithivMLmods/DeepAttriCap-VLA-3B +datasets: +- prithivMLmods/blip3o-caption-mini-arrow +- prithivMLmods/Caption3o-Opt-v3 +- prithivMLmods/Caption3o-Opt-v2 +- Multimodal-Fatima/Caltech101_not_background_test_facebook_opt_2.7b_Attributes_Caption_ns_5647 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- VisualUnderstanding +- text-generation-inference +- VisionLanguageAttribution +- AttributeCaptioning +- VLA +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/DeepAttriCap-VLA-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepAttriCap-VLA-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-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/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepAttriCap-VLA-3B-GGUF/resolve/main/DeepAttriCap-VLA-3B.f16.gguf) | f16 | 6.3 | 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. + +