commit 5290552ef82ca6acea28a678cb26ff81f82b2c73 Author: ModelHub XC Date: Mon May 25 12:24:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a840003 --- /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 +OmniLong-Qwen2.5-VL-7B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OmniLong-Qwen2.5-VL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OmniLong-Qwen2.5-VL-7B.IQ4_XS.gguf b/OmniLong-Qwen2.5-VL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..6d407bd --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c76c3252e7051a51e49fbf89bd7e6ec1262166950607185fe7cc19fc9da8207 +size 4250298752 diff --git a/OmniLong-Qwen2.5-VL-7B.Q2_K.gguf b/OmniLong-Qwen2.5-VL-7B.Q2_K.gguf new file mode 100644 index 0000000..f940439 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b5a52fc9cd83a632e94af8b0d29c77a2c43b16e016decf0c6583aa1e6dfc10 +size 3015940480 diff --git a/OmniLong-Qwen2.5-VL-7B.Q3_K_L.gguf b/OmniLong-Qwen2.5-VL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..6903064 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225b5664e625619c4db2bd4615f10eade6eccc5965a4a59da1bf1e3803543aff +size 4088459648 diff --git a/OmniLong-Qwen2.5-VL-7B.Q3_K_M.gguf b/OmniLong-Qwen2.5-VL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..df92b1e --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26852cd65fa47bde581e1b722091b1c65617f846a4334c8263613f36d968ff7c +size 3808391552 diff --git a/OmniLong-Qwen2.5-VL-7B.Q3_K_S.gguf b/OmniLong-Qwen2.5-VL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..d4ca6af --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be246d109add70a438cf6e8b8ff9f4058707eec91244f52377844cee1a4c3e6b +size 3492368768 diff --git a/OmniLong-Qwen2.5-VL-7B.Q4_K_M.gguf b/OmniLong-Qwen2.5-VL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..953bfb0 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa08abee5d37e7c4a4888d5cff37f2838bb399938ca4baffc0f86a09c22294f +size 4683073920 diff --git a/OmniLong-Qwen2.5-VL-7B.Q4_K_S.gguf b/OmniLong-Qwen2.5-VL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..48728e5 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c545ee9af8c2e1ec57fe8fdece762d50d93f92a05d8c16c04f6326089502685f +size 4457769344 diff --git a/OmniLong-Qwen2.5-VL-7B.Q5_K_M.gguf b/OmniLong-Qwen2.5-VL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..d509a91 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c5c00573df5e896da439534edd9e59829ef6b5acca5018fcfd484383b63c69 +size 5444831616 diff --git a/OmniLong-Qwen2.5-VL-7B.Q5_K_S.gguf b/OmniLong-Qwen2.5-VL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..bf9f973 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff66d14ec0f8ec2b749b068580ca7b9f2d2ed9ae199c96afff85c678eeffcf14 +size 5315176832 diff --git a/OmniLong-Qwen2.5-VL-7B.Q6_K.gguf b/OmniLong-Qwen2.5-VL-7B.Q6_K.gguf new file mode 100644 index 0000000..e2c056d --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae34a3bb34dd5783faf3659d2df799a79c366cdd8191f4186ab96c5f18692ce9 +size 6254199168 diff --git a/OmniLong-Qwen2.5-VL-7B.Q8_0.gguf b/OmniLong-Qwen2.5-VL-7B.Q8_0.gguf new file mode 100644 index 0000000..c92820b --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4edac727797cf6b617212229618593bf95f9920b6fdd61a0b7dd5ee37c94c31c +size 8098525568 diff --git a/OmniLong-Qwen2.5-VL-7B.f16.gguf b/OmniLong-Qwen2.5-VL-7B.f16.gguf new file mode 100644 index 0000000..9563eb8 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d28ca13ee2c54ed8a8738fe676efa397f9f37aef5dd353ccaa7ab72aeabd78 +size 15237853568 diff --git a/OmniLong-Qwen2.5-VL-7B.mmproj-Q8_0.gguf b/OmniLong-Qwen2.5-VL-7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..cf844e7 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6df5b131b381028eab33a786f476156e3c92dfd7b067606574a371ad41a4d3 +size 853119744 diff --git a/OmniLong-Qwen2.5-VL-7B.mmproj-f16.gguf b/OmniLong-Qwen2.5-VL-7B.mmproj-f16.gguf new file mode 100644 index 0000000..58d48f5 --- /dev/null +++ b/OmniLong-Qwen2.5-VL-7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1256b35305dbe1011c5883f5460bfb9882fee4b47b72e94522e8aceaaa19e7 +size 1354162944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..253c251 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: aws-prototyping/OmniLong-Qwen2.5-VL-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/aws-prototyping/OmniLong-Qwen2.5-VL-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OmniLong-Qwen2.5-VL-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-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/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OmniLong-Qwen2.5-VL-7B-GGUF/resolve/main/OmniLong-Qwen2.5-VL-7B.f16.gguf) | f16 | 15.3 | 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. + +