commit 3e700fbc7c3d7617ca150bab1b510b6762707003 Author: ModelHub XC Date: Tue May 26 02:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2VL-7B-RS-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d04d7ab --- /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 +Qwen2VL-7B-RS.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-7B-RS.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2VL-7B-RS.IQ4_XS.gguf b/Qwen2VL-7B-RS.IQ4_XS.gguf new file mode 100644 index 0000000..a37a1f0 --- /dev/null +++ b/Qwen2VL-7B-RS.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3d763725d0694fabf1694476224258b767aade13f780709f4e10446a4db251 +size 4250297312 diff --git a/Qwen2VL-7B-RS.Q2_K.gguf b/Qwen2VL-7B-RS.Q2_K.gguf new file mode 100644 index 0000000..4c52542 --- /dev/null +++ b/Qwen2VL-7B-RS.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c021b0122dcaa687f63892350e01b9c6dd91e39f8ddcd80c2fe82fdf125436 +size 3015939040 diff --git a/Qwen2VL-7B-RS.Q3_K_L.gguf b/Qwen2VL-7B-RS.Q3_K_L.gguf new file mode 100644 index 0000000..9f98b26 --- /dev/null +++ b/Qwen2VL-7B-RS.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210d000faebb00222681febdaef09db60390ac16016369358958e851cac9b5c5 +size 4088458208 diff --git a/Qwen2VL-7B-RS.Q3_K_M.gguf b/Qwen2VL-7B-RS.Q3_K_M.gguf new file mode 100644 index 0000000..12315a1 --- /dev/null +++ b/Qwen2VL-7B-RS.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10657c6c4f4d6cc44c40c6ab1f0839aaaaf3a3b2f42d780aef4fbd9ceaf3ff31 +size 3808390112 diff --git a/Qwen2VL-7B-RS.Q3_K_S.gguf b/Qwen2VL-7B-RS.Q3_K_S.gguf new file mode 100644 index 0000000..bf207d6 --- /dev/null +++ b/Qwen2VL-7B-RS.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b114576e733ce9c1fc8dab5f9e8bc9fa27438bd69997f586e5b0d5ef2a33b913 +size 3492367328 diff --git a/Qwen2VL-7B-RS.Q4_K_M.gguf b/Qwen2VL-7B-RS.Q4_K_M.gguf new file mode 100644 index 0000000..f49cded --- /dev/null +++ b/Qwen2VL-7B-RS.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7541a5853c534250db62b868a736c60ee1de6bc0ba63e87b04c849ae80cb227c +size 4683072480 diff --git a/Qwen2VL-7B-RS.Q4_K_S.gguf b/Qwen2VL-7B-RS.Q4_K_S.gguf new file mode 100644 index 0000000..29c6ca3 --- /dev/null +++ b/Qwen2VL-7B-RS.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16dd66fed691ed36c9b720c84d53fc4976d99b196948850b5c04136fd7ea763d +size 4457767904 diff --git a/Qwen2VL-7B-RS.Q5_K_M.gguf b/Qwen2VL-7B-RS.Q5_K_M.gguf new file mode 100644 index 0000000..1e44bfc --- /dev/null +++ b/Qwen2VL-7B-RS.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099f9e94aebba801d0ced5dc552a7e5593dad3bc49f0413e58534063f06360dd +size 5444830176 diff --git a/Qwen2VL-7B-RS.Q5_K_S.gguf b/Qwen2VL-7B-RS.Q5_K_S.gguf new file mode 100644 index 0000000..82c4a69 --- /dev/null +++ b/Qwen2VL-7B-RS.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57e4326253e3fd471aa6308683f9631248cfcd85c40d904fdeebb7abff2855d +size 5315175392 diff --git a/Qwen2VL-7B-RS.Q6_K.gguf b/Qwen2VL-7B-RS.Q6_K.gguf new file mode 100644 index 0000000..53d9d45 --- /dev/null +++ b/Qwen2VL-7B-RS.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0410473e8f0c8450867504fc905ea158b638a1b6f6523a6ae76dda7976b05d +size 6254197728 diff --git a/Qwen2VL-7B-RS.Q8_0.gguf b/Qwen2VL-7B-RS.Q8_0.gguf new file mode 100644 index 0000000..e8e548f --- /dev/null +++ b/Qwen2VL-7B-RS.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b902408b18c56af3fc15b44045cd4294081ffaa12c55dc33f564ee1c9e6a25 +size 8098524128 diff --git a/Qwen2VL-7B-RS.f16.gguf b/Qwen2VL-7B-RS.f16.gguf new file mode 100644 index 0000000..711937b --- /dev/null +++ b/Qwen2VL-7B-RS.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c016baa00ccf2b10edb7498a7e685318867f9ad857e7befb9806bd685b1542f7 +size 15237852128 diff --git a/Qwen2VL-7B-RS.mmproj-Q8_0.gguf b/Qwen2VL-7B-RS.mmproj-Q8_0.gguf new file mode 100644 index 0000000..5539b5b --- /dev/null +++ b/Qwen2VL-7B-RS.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f87552e78b89f70185f1ce8382d5d4ed6e826d1de506c516782ba1ddd70d1f +size 721032288 diff --git a/Qwen2VL-7B-RS.mmproj-f16.gguf b/Qwen2VL-7B-RS.mmproj-f16.gguf new file mode 100644 index 0000000..9cd8127 --- /dev/null +++ b/Qwen2VL-7B-RS.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f65b183e516053c8cddedeb7f6e0ebf7d35d3878893ebaaea54d88d2141792 +size 1352635488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e43539c --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: PumpkinCat/Qwen2VL-7B-RS +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/PumpkinCat/Qwen2VL-7B-RS + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2VL-7B-RS-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-7B-RS-GGUF/resolve/main/Qwen2VL-7B-RS.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. + +