commit 31de0853627f9a3fbbcee3f728268e338ed3ae35 Author: ModelHub XC Date: Wed Jun 10 05:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Unicorn-VL-R3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..95c29df --- /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 +Unicorn-VL-R3.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Unicorn-VL-R3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5b32982 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: unicorn-team/Unicorn-VL-R3 +datasets: +- allenai/Dolci-Think-SFT-7B +- unicorn-team/dolci-vi-5k +- unicorn-team/unicorn-12task +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/unicorn-team/Unicorn-VL-R3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Unicorn-VL-R3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Unicorn-VL-R3-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/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Unicorn-VL-R3-GGUF/resolve/main/Unicorn-VL-R3.f16.gguf) | f16 | 16.5 | 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/Unicorn-VL-R3.IQ4_XS.gguf b/Unicorn-VL-R3.IQ4_XS.gguf new file mode 100644 index 0000000..c6f58e5 --- /dev/null +++ b/Unicorn-VL-R3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454be313341fa191d239073ed87a369296ef74c7523e2a93cea4db9b874e3b04 +size 4593298752 diff --git a/Unicorn-VL-R3.Q2_K.gguf b/Unicorn-VL-R3.Q2_K.gguf new file mode 100644 index 0000000..bee7f6f --- /dev/null +++ b/Unicorn-VL-R3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d9e8d5301f0918470a43fd3b0e1a369c0fb0e8b0224462970db19add71ed9a +size 3281734976 diff --git a/Unicorn-VL-R3.Q3_K_L.gguf b/Unicorn-VL-R3.Q3_K_L.gguf new file mode 100644 index 0000000..1cd037c --- /dev/null +++ b/Unicorn-VL-R3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3328bed7b968d7f02af3a8fd138a1fbf753e0bbd53d4d0db9995171945560290 +size 4431396160 diff --git a/Unicorn-VL-R3.Q3_K_M.gguf b/Unicorn-VL-R3.Q3_K_M.gguf new file mode 100644 index 0000000..3b0fd0f --- /dev/null +++ b/Unicorn-VL-R3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d12e879cb7906b4463d5b148f75ad31174b3dbe924675912ef381e5cec0733b3 +size 4124163392 diff --git a/Unicorn-VL-R3.Q3_K_S.gguf b/Unicorn-VL-R3.Q3_K_S.gguf new file mode 100644 index 0000000..a712ce4 --- /dev/null +++ b/Unicorn-VL-R3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7239bec7915ef3079ed45202148db57dea70c6d02f3217d032da923a642e6d +size 3769613632 diff --git a/Unicorn-VL-R3.Q4_K_M.gguf b/Unicorn-VL-R3.Q4_K_M.gguf new file mode 100644 index 0000000..28d1314 --- /dev/null +++ b/Unicorn-VL-R3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5998d92e9fe16796a941d0f3268b996191db6caf7fa7ff18848fb7e9184c240 +size 5027786048 diff --git a/Unicorn-VL-R3.Q4_K_S.gguf b/Unicorn-VL-R3.Q4_K_S.gguf new file mode 100644 index 0000000..027ad62 --- /dev/null +++ b/Unicorn-VL-R3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90e213a3f7537d327cae49f56c8e80e385a0b908cd2bdea5d1a58ee7b5a5f31 +size 4802014528 diff --git a/Unicorn-VL-R3.Q5_K_M.gguf b/Unicorn-VL-R3.Q5_K_M.gguf new file mode 100644 index 0000000..1d695b0 --- /dev/null +++ b/Unicorn-VL-R3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd26e2b4d197b6a0dd6b3d843ce0b7b97967c52e14f8e8272d8be606102666c3 +size 5851114816 diff --git a/Unicorn-VL-R3.Q5_K_S.gguf b/Unicorn-VL-R3.Q5_K_S.gguf new file mode 100644 index 0000000..34cb0ab --- /dev/null +++ b/Unicorn-VL-R3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2760c7a12cbd2aee14d8bca3b2ea51fcc739bec64c81da29baeb3f08b19448 +size 5720763712 diff --git a/Unicorn-VL-R3.Q6_K.gguf b/Unicorn-VL-R3.Q6_K.gguf new file mode 100644 index 0000000..6bae612 --- /dev/null +++ b/Unicorn-VL-R3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ff1048f78ecca77be101a81804a8c9da60027b70373bf62588ad42d02579b8 +size 6725901632 diff --git a/Unicorn-VL-R3.Q8_0.gguf b/Unicorn-VL-R3.Q8_0.gguf new file mode 100644 index 0000000..0735cfd --- /dev/null +++ b/Unicorn-VL-R3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ae3b42baead18a2c6039f92a219e9d1018da163d5e1b27694f4a66f4bc07b7 +size 8709520704 diff --git a/Unicorn-VL-R3.f16.gguf b/Unicorn-VL-R3.f16.gguf new file mode 100644 index 0000000..b3b1662 --- /dev/null +++ b/Unicorn-VL-R3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91817927848f8f78da4cb58b1ded3b11442fc3d7773704dac170b0da9a1c217 +size 16388046144 diff --git a/Unicorn-VL-R3.mmproj-Q8_0.gguf b/Unicorn-VL-R3.mmproj-Q8_0.gguf new file mode 100644 index 0000000..e3dc919 --- /dev/null +++ b/Unicorn-VL-R3.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a3daa87e13cfccee0d72a40ac6dc981e604a84b969ed6575f4d8be49ea30d6 +size 752290624 diff --git a/Unicorn-VL-R3.mmproj-f16.gguf b/Unicorn-VL-R3.mmproj-f16.gguf new file mode 100644 index 0000000..979cb9b --- /dev/null +++ b/Unicorn-VL-R3.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98002f157e947cb3c209042c9a9c388a49f714fd7cb21c192f0d790631efed76 +size 1159030720