commit 7bc24f3cb6886cf6029c2c9301dda9a2be9757f9 Author: ModelHub XC Date: Fri May 8 17:14:43 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Flex-VL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..811bad4 --- /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 +Flex-VL-7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flex-VL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Flex-VL-7B.IQ4_XS.gguf b/Flex-VL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..c88f123 --- /dev/null +++ b/Flex-VL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380a1fe16973ef46db8dd1e28d5ad49ec6e9777fbf77d3cc200d6e7dc9a0d082 +size 4250297248 diff --git a/Flex-VL-7B.Q2_K.gguf b/Flex-VL-7B.Q2_K.gguf new file mode 100644 index 0000000..2ad8043 --- /dev/null +++ b/Flex-VL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c353149217323194d9eb71ea5444f515be1dbeb90cd744e0c67c28e4f3b0a679 +size 3015938976 diff --git a/Flex-VL-7B.Q3_K_L.gguf b/Flex-VL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..a590108 --- /dev/null +++ b/Flex-VL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e457a1956852df506f870c4b1fb65528a60fd74188a07cc3715c8f607d6daec +size 4088458144 diff --git a/Flex-VL-7B.Q3_K_M.gguf b/Flex-VL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..6356f54 --- /dev/null +++ b/Flex-VL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7a8b6eeb85bf44c07aa7d8a0e2f41fa5497de97d725c504aca6c450d4abceb +size 3808390048 diff --git a/Flex-VL-7B.Q3_K_S.gguf b/Flex-VL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..389cab2 --- /dev/null +++ b/Flex-VL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5263eddfb65f3f8f364dac5c0e104b944028e7ce61e1482eb86e90916c62adab +size 3492367264 diff --git a/Flex-VL-7B.Q4_K_M.gguf b/Flex-VL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..1eb7d1b --- /dev/null +++ b/Flex-VL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05315cfcc842f494d7113becff0ee47f413f9f525efd57a34fdb41ffacf0843c +size 4683072416 diff --git a/Flex-VL-7B.Q4_K_S.gguf b/Flex-VL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..ffa2775 --- /dev/null +++ b/Flex-VL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5d136d6d4d0bd59eea14b5260bfc91ba5c8b51e597aa0e7d3b3333eeb877e1 +size 4457767840 diff --git a/Flex-VL-7B.Q5_K_M.gguf b/Flex-VL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..ab74201 --- /dev/null +++ b/Flex-VL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da490d1b3b2684e31141d649a05035b5b47b1644fb294ea382c0ac0c181c9bf7 +size 5444830112 diff --git a/Flex-VL-7B.Q5_K_S.gguf b/Flex-VL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..3b1fbfb --- /dev/null +++ b/Flex-VL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefc7eacbb3de5bd9a0dec5b48c1b818b120d60e6dc21d517dd29b184de29b52 +size 5315175328 diff --git a/Flex-VL-7B.Q6_K.gguf b/Flex-VL-7B.Q6_K.gguf new file mode 100644 index 0000000..3a75cd6 --- /dev/null +++ b/Flex-VL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11135713087f03a6aca8486d2eb23699c6e7fa9a5539fd074c6fccae8ccd2107 +size 6254197664 diff --git a/Flex-VL-7B.Q8_0.gguf b/Flex-VL-7B.Q8_0.gguf new file mode 100644 index 0000000..904a528 --- /dev/null +++ b/Flex-VL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f91b49caef69a156411dd88b3801bbeb6a654640e0a31ad3558c686dce1d2e +size 8098524064 diff --git a/Flex-VL-7B.f16.gguf b/Flex-VL-7B.f16.gguf new file mode 100644 index 0000000..af719bc --- /dev/null +++ b/Flex-VL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125343ab0577c09f16aadb2f042b4fe34758898cab4f3586d7f6873c78a6d4c8 +size 15237852064 diff --git a/Flex-VL-7B.mmproj-Q8_0.gguf b/Flex-VL-7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..c6abeea --- /dev/null +++ b/Flex-VL-7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff555d8a6b527789b297c73cf853bab408d36e8dc6a920f2abe05ac8603c21e +size 853119680 diff --git a/Flex-VL-7B.mmproj-f16.gguf b/Flex-VL-7B.mmproj-f16.gguf new file mode 100644 index 0000000..97555fd --- /dev/null +++ b/Flex-VL-7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df26db5bd689dcab1ece856de8fa07e919b90f988d92ec1e52856fc8590029e +size 1354162880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ca7b7f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: jongwooko/Flex-VL-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jongwooko/Flex-VL-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Flex-VL-7B-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/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Flex-VL-7B-GGUF/resolve/main/Flex-VL-7B.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. + +