commit c1096c173c1fc89329c7a602f627e8dfc567edb0 Author: ModelHub XC Date: Tue Jun 2 11:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CapRL-Qwen3VL-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..55c0a67 --- /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 +CapRL-Qwen3VL-4B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CapRL-Qwen3VL-4B.IQ4_XS.gguf b/CapRL-Qwen3VL-4B.IQ4_XS.gguf new file mode 100644 index 0000000..a8dd298 --- /dev/null +++ b/CapRL-Qwen3VL-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae5c43bb1350265501faeac511de0a5c682d4f310762da410ea7e367bc5dd13 +size 2492951072 diff --git a/CapRL-Qwen3VL-4B.Q2_K.gguf b/CapRL-Qwen3VL-4B.Q2_K.gguf new file mode 100644 index 0000000..825cfa2 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32785d204ce716a434a570978b823cf0b075381875c2f4eadd37dab9fd468374 +size 1797127712 diff --git a/CapRL-Qwen3VL-4B.Q3_K_L.gguf b/CapRL-Qwen3VL-4B.Q3_K_L.gguf new file mode 100644 index 0000000..17e5599 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e24c57433c4057a2e1df092606ba8345e53344fd0608927bd406f680f92e072 +size 2406917152 diff --git a/CapRL-Qwen3VL-4B.Q3_K_M.gguf b/CapRL-Qwen3VL-4B.Q3_K_M.gguf new file mode 100644 index 0000000..68bcf54 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f38ae1f47aaaed1dead1af3e07c6720badbb27cc67c36e0a520ebe638d3bce +size 2242749472 diff --git a/CapRL-Qwen3VL-4B.Q3_K_S.gguf b/CapRL-Qwen3VL-4B.Q3_K_S.gguf new file mode 100644 index 0000000..a500085 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f72fbdce31b21ed34f76467a7996a0a51c83fb3d4357087df36561069cbc46 +size 2054128672 diff --git a/CapRL-Qwen3VL-4B.Q4_K_M.gguf b/CapRL-Qwen3VL-4B.Q4_K_M.gguf new file mode 100644 index 0000000..387c82e --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7bc45626c47ae700a95348e2a3f897e2dcbad79374236ce2467c7f291f3dcd +size 2716070432 diff --git a/CapRL-Qwen3VL-4B.Q4_K_S.gguf b/CapRL-Qwen3VL-4B.Q4_K_S.gguf new file mode 100644 index 0000000..152752c --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f4ce345cdb6182ff41ff33802cfb0740b13a848495cb1c6f9c6449bd912519 +size 2602099232 diff --git a/CapRL-Qwen3VL-4B.Q5_K_M.gguf b/CapRL-Qwen3VL-4B.Q5_K_M.gguf new file mode 100644 index 0000000..6d0fa05 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6d6e6790dcca8267edca40c91d45dba39ec1c28a7dc8328b898861cecb557a +size 3156922912 diff --git a/CapRL-Qwen3VL-4B.Q5_K_S.gguf b/CapRL-Qwen3VL-4B.Q5_K_S.gguf new file mode 100644 index 0000000..e864eee --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f1cad639b66855c2834c6fc825275e831343ff01fcb4047d07eff2168c0561 +size 3091120672 diff --git a/CapRL-Qwen3VL-4B.Q6_K.gguf b/CapRL-Qwen3VL-4B.Q6_K.gguf new file mode 100644 index 0000000..fda20e3 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4f6fb57984073e3b22d7b248743580dc5ee0ab29bf1848ad346718d9e72b0c +size 3625328672 diff --git a/CapRL-Qwen3VL-4B.Q8_0.gguf b/CapRL-Qwen3VL-4B.Q8_0.gguf new file mode 100644 index 0000000..7340355 --- /dev/null +++ b/CapRL-Qwen3VL-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81813b3c0606f81c63f27fb8df18f0f04e106c1955e3738d9decc8c4f684872f +size 4693672992 diff --git a/CapRL-Qwen3VL-4B.f16.gguf b/CapRL-Qwen3VL-4B.f16.gguf new file mode 100644 index 0000000..297fec9 --- /dev/null +++ b/CapRL-Qwen3VL-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b9912824d55a0e472c6c0dc60adb48f40d93fedc43b071b5a8ad1fd49ecc46 +size 8829199392 diff --git a/CapRL-Qwen3VL-4B.mmproj-Q8_0.gguf b/CapRL-Qwen3VL-4B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..e0ffa16 --- /dev/null +++ b/CapRL-Qwen3VL-4B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a867d3c14b6675fc4099e73d15e735abce13bd0e1e8a1c15febbffc4fff6d0d +size 453974720 diff --git a/CapRL-Qwen3VL-4B.mmproj-f16.gguf b/CapRL-Qwen3VL-4B.mmproj-f16.gguf new file mode 100644 index 0000000..ba6c0fb --- /dev/null +++ b/CapRL-Qwen3VL-4B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b444bc22eb8062feb5c0abe48f201e65368239b5832a792a1616348d35fcf0d +size 836180672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5eee51f --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: internlm/CapRL-Qwen3VL-4B +datasets: +- internlm/CapRL-2M +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- multimodal +- image caption +- captioning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/internlm/CapRL-Qwen3VL-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CapRL-Qwen3VL-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-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/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B.f16.gguf) | f16 | 8.9 | 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. + +