commit 469379d45d8cf607925436a3b7360e64bb0cd53c Author: ModelHub XC Date: Mon May 25 10:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolVLM2-2.2B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0c36b86 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +SmolVLM2-2.2B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolVLM2-2.2B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dad61d2 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: HuggingFaceTB/SmolVLM2-2.2B-Instruct +datasets: +- HuggingFaceM4/the_cauldron +- HuggingFaceM4/Docmatix +- lmms-lab/LLaVA-OneVision-Data +- lmms-lab/M4-Instruct-Data +- HuggingFaceFV/finevideo +- MAmmoTH-VL/MAmmoTH-VL-Instruct-12M +- lmms-lab/LLaVA-Video-178K +- orrzohar/Video-STaR +- Mutonix/Vript +- TIGER-Lab/VISTA-400K +- Enxin/MovieChat-1K_train +- ShareGPT4Video/ShareGPT4Video +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- video-text-to-text +--- +## About + + + + + + +static quants of https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmolVLM2-2.2B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-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/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.f16.gguf) | f16 | 3.7 | 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. + + diff --git a/SmolVLM2-2.2B-Instruct.IQ4_XS.gguf b/SmolVLM2-2.2B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..c011cb3 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e96884659018ca30e8bb3ba2b91bc7a9157509bf2c56102b91c2dcabc16167e +size 1002101216 diff --git a/SmolVLM2-2.2B-Instruct.Q2_K.gguf b/SmolVLM2-2.2B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..84b5f36 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb984933550e189fc29380b3c5c51ab2393db592cc6f78b90a6fd7212bf78108 +size 707922400 diff --git a/SmolVLM2-2.2B-Instruct.Q3_K_L.gguf b/SmolVLM2-2.2B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..988da83 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1854a57599946eba7d80e05c87b6a4b03b87e4d2c70321e6ec53be0ef80eae23 +size 976122336 diff --git a/SmolVLM2-2.2B-Instruct.Q3_K_M.gguf b/SmolVLM2-2.2B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..bc5e4ed --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e95ab64967e01fce500e142d5df75c2e06077ef8249bfa2eea2f4d441f43ad1 +size 903770592 diff --git a/SmolVLM2-2.2B-Instruct.Q3_K_S.gguf b/SmolVLM2-2.2B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..3f5a737 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb096c1500fdcabf6e94c9a78141f727046505fa60b5984ebb41fc74b8a8d293 +size 820408800 diff --git a/SmolVLM2-2.2B-Instruct.Q4_K_M.gguf b/SmolVLM2-2.2B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..202994e --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0887067c02e090820d53c157e448ba5bcf77a4e8489b570b200dfaa91c4489c7 +size 1112603104 diff --git a/SmolVLM2-2.2B-Instruct.Q4_K_S.gguf b/SmolVLM2-2.2B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c6d9bc8 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1adf82d916c95d245c1500767ad2e7b6ee4fa832cfe6bee0267c16c0343a067 +size 1056111072 diff --git a/SmolVLM2-2.2B-Instruct.Q5_K_M.gguf b/SmolVLM2-2.2B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..0705b77 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9d7f3599f0401dfd6d3b8d228d8975bb7885897dc96d6cdc1eacd2ef8b1a4b +size 1295088096 diff --git a/SmolVLM2-2.2B-Instruct.Q5_K_S.gguf b/SmolVLM2-2.2B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..87f0527 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44381384e91582b577e7a300230f747d8594cbc54811d995b79e964438a6fc20 +size 1261664736 diff --git a/SmolVLM2-2.2B-Instruct.Q6_K.gguf b/SmolVLM2-2.2B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..1f94513 --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e413f9393e49bd39dd32a549c1fc6def372190eef6533db6404c54d9747072 +size 1488978400 diff --git a/SmolVLM2-2.2B-Instruct.Q8_0.gguf b/SmolVLM2-2.2B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..547367f --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7180a083b84b7576233ddd67ecf50bb4932e4ef774eefc4b0f85964f855660 +size 1927934432 diff --git a/SmolVLM2-2.2B-Instruct.f16.gguf b/SmolVLM2-2.2B-Instruct.f16.gguf new file mode 100644 index 0000000..dd4115a --- /dev/null +++ b/SmolVLM2-2.2B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7123d144b89ea68cd48e28b6c523d57a8ce840949fc7a3418b01aa00732e37e8 +size 3627119072