commit 68b39320f2e5aa38fb3acac132a049834172d63d Author: ModelHub XC Date: Sun Jul 12 20:06:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Pegon-AI-VL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dbd8e24 --- /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 +Pegon-AI-VL.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Pegon-AI-VL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Pegon-AI-VL.IQ4_XS.gguf b/Pegon-AI-VL.IQ4_XS.gguf new file mode 100644 index 0000000..6ccd4fa --- /dev/null +++ b/Pegon-AI-VL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4b347b8e35273f0a86fadf0a8c3a4254fb809e65461fe8a4767388cf5dc8d9 +size 1016282880 diff --git a/Pegon-AI-VL.Q2_K.gguf b/Pegon-AI-VL.Q2_K.gguf new file mode 100644 index 0000000..4d3d0d3 --- /dev/null +++ b/Pegon-AI-VL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32570a2f994c704ad400ef09d87afba91fcd3629011357b92573127b42e64c45 +size 777797376 diff --git a/Pegon-AI-VL.Q3_K_L.gguf b/Pegon-AI-VL.Q3_K_L.gguf new file mode 100644 index 0000000..5001f27 --- /dev/null +++ b/Pegon-AI-VL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc564ba7f2dc4b034146ece729fde0baf30047da9951459639e4d79d85abd76 +size 1003503360 diff --git a/Pegon-AI-VL.Q3_K_M.gguf b/Pegon-AI-VL.Q3_K_M.gguf new file mode 100644 index 0000000..f80c882 --- /dev/null +++ b/Pegon-AI-VL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc69ac4713c25f5a7c7b38d113517aa967e033e36a20aa469b48ab84802e39a +size 939540224 diff --git a/Pegon-AI-VL.Q3_K_S.gguf b/Pegon-AI-VL.Q3_K_S.gguf new file mode 100644 index 0000000..8bbe9cc --- /dev/null +++ b/Pegon-AI-VL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba1b2cf57e8a45b790065a2ac6e37b0b2324ad6bfb0e583affc79fa9826acda +size 867254016 diff --git a/Pegon-AI-VL.Q4_K_M.gguf b/Pegon-AI-VL.Q4_K_M.gguf new file mode 100644 index 0000000..751ac94 --- /dev/null +++ b/Pegon-AI-VL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1ad642a47bca907f4d70fb836a703aac7a79e1b349d0b8bcf7cd4b2ce901c8 +size 1107410688 diff --git a/Pegon-AI-VL.Q4_K_S.gguf b/Pegon-AI-VL.Q4_K_S.gguf new file mode 100644 index 0000000..35de3f2 --- /dev/null +++ b/Pegon-AI-VL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea8af90ad22eb36d723cec50d73de0f5836c168f8c9bab5e5985498a03a0757 +size 1060192000 diff --git a/Pegon-AI-VL.Q5_K_M.gguf b/Pegon-AI-VL.Q5_K_M.gguf new file mode 100644 index 0000000..e41142d --- /dev/null +++ b/Pegon-AI-VL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247077fd705ed2e2991f935fd0fe2489bc26fa145b7619effd34ce42f07d3a34 +size 1257881344 diff --git a/Pegon-AI-VL.Q5_K_S.gguf b/Pegon-AI-VL.Q5_K_S.gguf new file mode 100644 index 0000000..980cc11 --- /dev/null +++ b/Pegon-AI-VL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349c29dfbfeea3456bf2cd86df22b357d1118873aa9ef095df86e2a474752221 +size 1230585600 diff --git a/Pegon-AI-VL.Q6_K.gguf b/Pegon-AI-VL.Q6_K.gguf new file mode 100644 index 0000000..25474de --- /dev/null +++ b/Pegon-AI-VL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388558487337afc6b0aa1ebfab7d28d993a7ea56d7f714e6cd89ef00282b0e16 +size 1417756416 diff --git a/Pegon-AI-VL.Q8_0.gguf b/Pegon-AI-VL.Q8_0.gguf new file mode 100644 index 0000000..6649546 --- /dev/null +++ b/Pegon-AI-VL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492d03abdd4af87c25c631992810410bf964cf95d075d7a21b19c148a417b854 +size 1834428160 diff --git a/Pegon-AI-VL.f16.gguf b/Pegon-AI-VL.f16.gguf new file mode 100644 index 0000000..a71d9e2 --- /dev/null +++ b/Pegon-AI-VL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5de8c33a3b40945b46b9ebee73eb0620e6a495854e86ea5426f1f06faf90cf3 +size 3447351040 diff --git a/Pegon-AI-VL.mmproj-Q8_0.gguf b/Pegon-AI-VL.mmproj-Q8_0.gguf new file mode 100644 index 0000000..46717a2 --- /dev/null +++ b/Pegon-AI-VL.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1bf47afb1a7a65d4dea7e71b976768f9d7c2fbe497fb887020e1aa78a977a0 +size 445053472 diff --git a/Pegon-AI-VL.mmproj-f16.gguf b/Pegon-AI-VL.mmproj-f16.gguf new file mode 100644 index 0000000..f90e0be --- /dev/null +++ b/Pegon-AI-VL.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a762540079ec68260d7971e09def653754f92275f77a21a17aa03b2d6564c9b1 +size 819395104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..12fe516 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: kucingcoder/Pegon-AI-VL +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gguf +- llama.cpp +- unsloth +- vision-language-model +--- +## About + + + + + + + + + +static quants of https://huggingface.co/kucingcoder/Pegon-AI-VL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Pegon-AI-VL-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Pegon-AI-VL-GGUF/resolve/main/Pegon-AI-VL.f16.gguf) | f16 | 3.5 | 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. + +