commit 3c2477cc02195f2d9b8f644eb360a52fa67dd52f Author: ModelHub XC Date: Tue May 12 06:28:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenSearch-VL-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0e1059 --- /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 +OpenSearch-VL-8B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenSearch-VL-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenSearch-VL-8B.IQ4_XS.gguf b/OpenSearch-VL-8B.IQ4_XS.gguf new file mode 100644 index 0000000..52e3048 --- /dev/null +++ b/OpenSearch-VL-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0637ed57e84a84f0b45f9e1e1e8433b884411a505450e3063e1a40077b9e99fb +size 4593298816 diff --git a/OpenSearch-VL-8B.Q2_K.gguf b/OpenSearch-VL-8B.Q2_K.gguf new file mode 100644 index 0000000..5f5a077 --- /dev/null +++ b/OpenSearch-VL-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfa0e2054bd601b0f7cd7ca4e770927f4843eb4e64ca3100f1f73e276b1625d +size 3281735040 diff --git a/OpenSearch-VL-8B.Q3_K_L.gguf b/OpenSearch-VL-8B.Q3_K_L.gguf new file mode 100644 index 0000000..f35af96 --- /dev/null +++ b/OpenSearch-VL-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44730303a1d0b0b33b39c7d7e32a3341a657113b76161c07ab9dc54205fc3db1 +size 4431396224 diff --git a/OpenSearch-VL-8B.Q3_K_M.gguf b/OpenSearch-VL-8B.Q3_K_M.gguf new file mode 100644 index 0000000..777f314 --- /dev/null +++ b/OpenSearch-VL-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d76afb0add459a6a08b52fbf49da5fd7775fd8841d2350dd1a99f9980689438 +size 4124163456 diff --git a/OpenSearch-VL-8B.Q3_K_S.gguf b/OpenSearch-VL-8B.Q3_K_S.gguf new file mode 100644 index 0000000..8df9525 --- /dev/null +++ b/OpenSearch-VL-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978db4d537687be82362d025cf5e20e65f22ef46070bf500978b88ee9f762f99 +size 3769613696 diff --git a/OpenSearch-VL-8B.Q4_K_M.gguf b/OpenSearch-VL-8B.Q4_K_M.gguf new file mode 100644 index 0000000..010959b --- /dev/null +++ b/OpenSearch-VL-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b95f002cf2561a28e43955eaf01e796e9aa4cc71ce8a14abcd0463172a35e5a +size 5027786112 diff --git a/OpenSearch-VL-8B.Q4_K_S.gguf b/OpenSearch-VL-8B.Q4_K_S.gguf new file mode 100644 index 0000000..e72db7b --- /dev/null +++ b/OpenSearch-VL-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13bee9cdb5d3a5b18ab61349eb0e7021f9490e725d09f1bf81bf65196b4e2ab6 +size 4802014592 diff --git a/OpenSearch-VL-8B.Q5_K_M.gguf b/OpenSearch-VL-8B.Q5_K_M.gguf new file mode 100644 index 0000000..59ddc88 --- /dev/null +++ b/OpenSearch-VL-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79260ff5f807c5bf8e9f30616dcdec7347bc0e3aa133919ffdf2980952bfd150 +size 5851114880 diff --git a/OpenSearch-VL-8B.Q5_K_S.gguf b/OpenSearch-VL-8B.Q5_K_S.gguf new file mode 100644 index 0000000..119e729 --- /dev/null +++ b/OpenSearch-VL-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291930e45ccd239f6f0e9e7a3212c7598ec7a7f6c7ef779c96703b8da76da89c +size 5720763776 diff --git a/OpenSearch-VL-8B.Q6_K.gguf b/OpenSearch-VL-8B.Q6_K.gguf new file mode 100644 index 0000000..8f7b9c0 --- /dev/null +++ b/OpenSearch-VL-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd1efe61fda8994d5b2c79af6cbe78cdd39e610e9dda9ac05199e99d1dcdaec +size 6725901696 diff --git a/OpenSearch-VL-8B.Q8_0.gguf b/OpenSearch-VL-8B.Q8_0.gguf new file mode 100644 index 0000000..d4dd4b4 --- /dev/null +++ b/OpenSearch-VL-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b10baba114470c4e264a2cec48bed25cc9a61a7e7efca40f0a482d95b759a2d +size 8709520768 diff --git a/OpenSearch-VL-8B.f16.gguf b/OpenSearch-VL-8B.f16.gguf new file mode 100644 index 0000000..d5f3d48 --- /dev/null +++ b/OpenSearch-VL-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228010212d3dcac261a4d7664fac121ed2f2c56ce4556f8e822d1fd1fd31bee7 +size 16388046208 diff --git a/OpenSearch-VL-8B.mmproj-Q8_0.gguf b/OpenSearch-VL-8B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..fef4756 --- /dev/null +++ b/OpenSearch-VL-8B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:705b59cefe230a27453d80908b645c290375017bcf254930b766fa9e8cbffd73 +size 752290624 diff --git a/OpenSearch-VL-8B.mmproj-f16.gguf b/OpenSearch-VL-8B.mmproj-f16.gguf new file mode 100644 index 0000000..d2f3481 --- /dev/null +++ b/OpenSearch-VL-8B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a94f2755fe612dbb7bf46a812be6385fe6938f207b9f28603b55e1c6d2dc61b7 +size 1159030720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a64fa00 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: OpenSearch-VL/OpenSearch-VL-8B +datasets: +- OpenSearch-VL/Search-VL-SFT-36K +- OpenSearch-VL/Search-VL-RL-8K +language: +- en +- zh +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/OpenSearch-VL/OpenSearch-VL-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OpenSearch-VL-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenSearch-VL-8B-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/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenSearch-VL-8B-GGUF/resolve/main/OpenSearch-VL-8B.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. + +