commit f9996fb9d66e2a933939449192a06da099cc2a90 Author: ModelHub XC Date: Mon Oct 19 03:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/UI-TARS-2B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed5a031 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +UI-TARS-2B-SFT.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +UI-TARS-2B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a63aaa --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ByteDance-Seed/UI-TARS-2B-SFT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- multimodal +- gui +--- +## About + + + + + + +static quants of https://huggingface.co/ByteDance-Seed/UI-TARS-2B-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/UI-TARS-2B-SFT-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/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/UI-TARS-2B-SFT-GGUF/resolve/main/UI-TARS-2B-SFT.f16.gguf) | f16 | 3.7 | 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/UI-TARS-2B-SFT.IQ4_XS.gguf b/UI-TARS-2B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..e4df8b6 --- /dev/null +++ b/UI-TARS-2B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210bf8126fabd61c341d85f03d7ec7edbe19be0919afddc1937fd454cd5dc326 +size 1026161376 diff --git a/UI-TARS-2B-SFT.Q2_K.gguf b/UI-TARS-2B-SFT.Q2_K.gguf new file mode 100644 index 0000000..07e700b --- /dev/null +++ b/UI-TARS-2B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de295e59fee2423fcec25a102025118fcae93dfa09556d1f6150ab42304e5f9 +size 752879328 diff --git a/UI-TARS-2B-SFT.Q3_K_L.gguf b/UI-TARS-2B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..28d7d9f --- /dev/null +++ b/UI-TARS-2B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd02ffd473260657519265cd39ab4fcf5ed260e8e35165536737662a24697ce +size 980439264 diff --git a/UI-TARS-2B-SFT.Q3_K_M.gguf b/UI-TARS-2B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..2f4046f --- /dev/null +++ b/UI-TARS-2B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a611c9f70dc92e7ec228e61be31b282364434592e11a76eb29e017fec8f2535 +size 924455136 diff --git a/UI-TARS-2B-SFT.Q3_K_S.gguf b/UI-TARS-2B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..a7d0add --- /dev/null +++ b/UI-TARS-2B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1a18bd0ebd2b2e1382790bea3432b68d077cdcb761ad8bc0e1ed4e3d1c6ed1 +size 861221088 diff --git a/UI-TARS-2B-SFT.Q4_K_M.gguf b/UI-TARS-2B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..764673c --- /dev/null +++ b/UI-TARS-2B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de211ed1f8d8b3847e90e98d259448f72774b81a0486e260e2d80126e823fb6a +size 1117319904 diff --git a/UI-TARS-2B-SFT.Q4_K_S.gguf b/UI-TARS-2B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..e90086a --- /dev/null +++ b/UI-TARS-2B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db5127a0204e6f3af87045f0ffb13fa81d4170a5d39d5427bf317c2487b9939 +size 1071583968 diff --git a/UI-TARS-2B-SFT.Q5_K_M.gguf b/UI-TARS-2B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..bddd0e0 --- /dev/null +++ b/UI-TARS-2B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc9472e87571e336fd473f7e545a6677734bb307ea8267392bf9667f7e004e0 +size 1285493472 diff --git a/UI-TARS-2B-SFT.Q5_K_S.gguf b/UI-TARS-2B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..4b5ca4f --- /dev/null +++ b/UI-TARS-2B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bfd433b55e17bd146fab26696a9d0cdaaa44430714595444123e09dff35f6d2 +size 1259172576 diff --git a/UI-TARS-2B-SFT.Q6_K.gguf b/UI-TARS-2B-SFT.Q6_K.gguf new file mode 100644 index 0000000..4f8adeb --- /dev/null +++ b/UI-TARS-2B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de25385406d3dc322252f6616a9ca6d72efad466f6a45501c994b30ff1e2fd36 +size 1464177888 diff --git a/UI-TARS-2B-SFT.Q8_0.gguf b/UI-TARS-2B-SFT.Q8_0.gguf new file mode 100644 index 0000000..495d42f --- /dev/null +++ b/UI-TARS-2B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2278098869137a0edad84bfc6f5cd73aa1520f3b26d8fe4546f7b08dd9d43fb2 +size 1894531296 diff --git a/UI-TARS-2B-SFT.f16.gguf b/UI-TARS-2B-SFT.f16.gguf new file mode 100644 index 0000000..a8da095 --- /dev/null +++ b/UI-TARS-2B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fb50f867ade0df4ab4c17837502f3bf50bfc9f22d97c48bf0fd18b88c68b6f +size 3560415456 diff --git a/UI-TARS-2B-SFT.mmproj-fp16.gguf b/UI-TARS-2B-SFT.mmproj-fp16.gguf new file mode 100644 index 0000000..dd68aaa --- /dev/null +++ b/UI-TARS-2B-SFT.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9c248c4ff9770b3cd82d0ed5b5d377ea02500d8d22368db9b7c2d4476b32ce8 +size 1331656192