commit 6cb1797e0c9990ae87be904a9aef5426a314ce2f Author: ModelHub XC Date: Wed Jun 17 05:56:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InternVL2_5-4B-MPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7416ade --- /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 +InternVL2_5-4B-MPO.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL2_5-4B-MPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InternVL2_5-4B-MPO.IQ4_XS.gguf b/InternVL2_5-4B-MPO.IQ4_XS.gguf new file mode 100644 index 0000000..05f6b80 --- /dev/null +++ b/InternVL2_5-4B-MPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4effac83f7a21fe577c09033d0b943cac750baa7fd1482d5851b71f64cec9fe0 +size 1917760864 diff --git a/InternVL2_5-4B-MPO.Q2_K.gguf b/InternVL2_5-4B-MPO.Q2_K.gguf new file mode 100644 index 0000000..899f969 --- /dev/null +++ b/InternVL2_5-4B-MPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cffd7cec06260d0740956cd669e31ef685755a97bb088ff587f05addb7468c +size 1376235296 diff --git a/InternVL2_5-4B-MPO.Q3_K_L.gguf b/InternVL2_5-4B-MPO.Q3_K_L.gguf new file mode 100644 index 0000000..876a06d --- /dev/null +++ b/InternVL2_5-4B-MPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d29104bfa05b97feca8fdfcfccc6d0d67a83eb6f5c83a84d83834b7f347718 +size 1840419392 diff --git a/InternVL2_5-4B-MPO.Q3_K_M.gguf b/InternVL2_5-4B-MPO.Q3_K_M.gguf new file mode 100644 index 0000000..9767ae3 --- /dev/null +++ b/InternVL2_5-4B-MPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4630d07e356ad549dc1ff3925f0a4c1fcdc611e5f2bd8d2fe35d25320bac9b +size 1723503168 diff --git a/InternVL2_5-4B-MPO.Q3_K_S.gguf b/InternVL2_5-4B-MPO.Q3_K_S.gguf new file mode 100644 index 0000000..79d56d6 --- /dev/null +++ b/InternVL2_5-4B-MPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7752a61293a16d7d08fcea00284015e1896eea3c9f5111bf0e101372354adc +size 1587384896 diff --git a/InternVL2_5-4B-MPO.Q4_K_M.gguf b/InternVL2_5-4B-MPO.Q4_K_M.gguf new file mode 100644 index 0000000..f9d734e --- /dev/null +++ b/InternVL2_5-4B-MPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b9e116fa1d5de8d859a52c6e7eaadbdb6ede12455ed4b08a660ba3a25f059ec +size 2104185824 diff --git a/InternVL2_5-4B-MPO.Q4_K_S.gguf b/InternVL2_5-4B-MPO.Q4_K_S.gguf new file mode 100644 index 0000000..b0b2a8d --- /dev/null +++ b/InternVL2_5-4B-MPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c77541f8ad5a0310802fc84f9266066f97323281d2284724e066c316467898b +size 2008667104 diff --git a/InternVL2_5-4B-MPO.Q5_K_M.gguf b/InternVL2_5-4B-MPO.Q5_K_M.gguf new file mode 100644 index 0000000..4605142 --- /dev/null +++ b/InternVL2_5-4B-MPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f2b8b658f5bb9aa17f34ddbcc3fec91696013bfc85eb1803a1a346cda2a803 +size 2437926368 diff --git a/InternVL2_5-4B-MPO.Q5_K_S.gguf b/InternVL2_5-4B-MPO.Q5_K_S.gguf new file mode 100644 index 0000000..2038738 --- /dev/null +++ b/InternVL2_5-4B-MPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907ae8fd8e9333efb5daae125d3a09bb96ea6a58735d356cdaf0f2cc06b5bb86 +size 2382777824 diff --git a/InternVL2_5-4B-MPO.Q6_K.gguf b/InternVL2_5-4B-MPO.Q6_K.gguf new file mode 100644 index 0000000..25cb2f5 --- /dev/null +++ b/InternVL2_5-4B-MPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0964e039d8ccc9871386ab303e8ee516a6e3b313154242e3e318261e1333b99 +size 2792525696 diff --git a/InternVL2_5-4B-MPO.Q8_0.gguf b/InternVL2_5-4B-MPO.Q8_0.gguf new file mode 100644 index 0000000..5b6bb8c --- /dev/null +++ b/InternVL2_5-4B-MPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fc56b503087fdb398af219c633b68089dcd0fd7cdaf946dbf670f4b0edd668 +size 3614943296 diff --git a/InternVL2_5-4B-MPO.f16.gguf b/InternVL2_5-4B-MPO.f16.gguf new file mode 100644 index 0000000..c25d155 --- /dev/null +++ b/InternVL2_5-4B-MPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cff108a74995b1cc550474c583b9e018243d911e449b3b269546f69bcf4ad0a +size 6798495296 diff --git a/InternVL2_5-4B-MPO.mmproj-Q8_0.gguf b/InternVL2_5-4B-MPO.mmproj-Q8_0.gguf new file mode 100644 index 0000000..fea1e20 --- /dev/null +++ b/InternVL2_5-4B-MPO.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a686ca710df95bee4cadc9959ad81b8303685fa80c9e603c00ac49f7501e002b +size 341194144 diff --git a/InternVL2_5-4B-MPO.mmproj-f16.gguf b/InternVL2_5-4B-MPO.mmproj-f16.gguf new file mode 100644 index 0000000..87c8647 --- /dev/null +++ b/InternVL2_5-4B-MPO.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369dcad4ce53e5e3aaa6cf66e7834db9a45d434f7ed7c4e2e11d8f973d60847c +size 636106144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..049dec5 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: OpenGVLab/InternVL2_5-4B-MPO +datasets: +- OpenGVLab/MMPR-v1.1 +language: +- multilingual +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- internvl +- custom_code +--- +## About + + + + + + +static quants of https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InternVL2_5-4B-MPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-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/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.mmproj-f16.gguf) | mmproj-f16 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL2_5-4B-MPO-GGUF/resolve/main/InternVL2_5-4B-MPO.f16.gguf) | f16 | 6.9 | 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. + +