commit 9943ea8a30106b44f150ecc2f554a5ff32e87fd5 Author: ModelHub XC Date: Sun Jul 19 16:57:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1ea648 --- /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 +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Instruct-Unredacted-MAX.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.IQ4_XS.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.IQ4_XS.gguf new file mode 100644 index 0000000..692f7b1 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e7f5e4acc1da4c112e282c0c78debb5782620b766895781ff970e68e8e7b84 +size 1753184384 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q2_K.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q2_K.gguf new file mode 100644 index 0000000..e6595e5 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6cc181fe3178e63067b225a416c10fe691cb650aac4f4b7699670cba3e6070 +size 1274755200 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_L.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_L.gguf new file mode 100644 index 0000000..c6d7281 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a9c8f210badbcdc73138710c0b224d546ac39c234beaa96c70821a1acd23a0 +size 1707391104 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_M.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_M.gguf new file mode 100644 index 0000000..c63f587 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd12dcff4282a868aaed976e1190599f806f507d11718d8ae80fac783d105b2c +size 1590474880 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_S.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_S.gguf new file mode 100644 index 0000000..8979297 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba81df98014bd678027286e3d6d17a5550e4750b23c7d54684416a5f2610ca8 +size 1454356608 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_M.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_M.gguf new file mode 100644 index 0000000..95ea421 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ca662452d12d095b8ade16ebbdd63a89ff56981bb54c71a5f5425cf7b440aa +size 1929902208 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_S.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_S.gguf new file mode 100644 index 0000000..8199e35 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e27052a7b68a7c3f27398702657832c7643920222da807607ba5cf0039ff96e +size 1834383488 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_M.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_M.gguf new file mode 100644 index 0000000..4d66433 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8db3bd5c4b0a6c28ca61108302ea988e2666a40ea9ca817af4de42a7b4a8f4 +size 2224814208 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_S.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_S.gguf new file mode 100644 index 0000000..a7087f7 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079194fa20a82b352c729f57666d8ac14c764dfd9ae40db8b42ab19668a9f724 +size 2169665664 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q6_K.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q6_K.gguf new file mode 100644 index 0000000..070729d --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95990aeb85d47d13ac820ff8384db3bc0592de3ebbe4e736528c4676dfcba6f0 +size 2538158208 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q8_0.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q8_0.gguf new file mode 100644 index 0000000..d667a9a --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8649d1f0e830fb08c5b6a4b2437500ddf9f0451859a408930606560d36d4614 +size 3285475456 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.f16.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.f16.gguf new file mode 100644 index 0000000..be48da1 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c8890f0550e3ea9d8e184f1dc8d8782c7674febb80ba19f8deec7ef959f18c +size 6178316416 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-Q8_0.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-Q8_0.gguf new file mode 100644 index 0000000..5ad5e70 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85662a176efff933524e4a622f8352d2edbfd3f748169359c9236d3a362b527 +size 847768928 diff --git a/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-f16.gguf b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-f16.gguf new file mode 100644 index 0000000..62c2fc2 --- /dev/null +++ b/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f68a18e8a2eb813bf0126f60abdfcae9c4ed300c6fee8a976b4c32b5f04d88 +size 1338428768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b72e40e --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- uncensored +- abliterated +- unfiltered +- unredacted +- vllm +- pytorch +- BF16 +- max +- legal +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-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/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Instruct-Unredacted-MAX-GGUF/resolve/main/Qwen2.5-VL-3B-Instruct-Unredacted-MAX.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. + +