commit 7149a9af0f127eae0cee4e6c2ac54b8f91f173da Author: ModelHub XC Date: Tue Jul 7 07:10:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lumian-VLR-7B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e38e84b --- /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 +Lumian-VLR-7B-Thinking.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lumian-VLR-7B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lumian-VLR-7B-Thinking.IQ4_XS.gguf b/Lumian-VLR-7B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..23d744d --- /dev/null +++ b/Lumian-VLR-7B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e389074df65b88a6c92c541fddf07ca80792e7d89f022bbd2cf6f41fd1581f55 +size 4250299136 diff --git a/Lumian-VLR-7B-Thinking.Q2_K.gguf b/Lumian-VLR-7B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..2039c80 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91aeef9a680620739e8eb0c53fcd0f23687c895dd52b982c29df7fd840f67f16 +size 3015940864 diff --git a/Lumian-VLR-7B-Thinking.Q3_K_L.gguf b/Lumian-VLR-7B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..b2197dc --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59012ea7e27fb53294e818b9cb708de6488c9a5ab464919b98fd3318fd9fe54 +size 4088460032 diff --git a/Lumian-VLR-7B-Thinking.Q3_K_M.gguf b/Lumian-VLR-7B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..a5d107e --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123df2cf4da19da231a128b5ee6d512b56d0f89069a5380ed691a749e1def36d +size 3808391936 diff --git a/Lumian-VLR-7B-Thinking.Q3_K_S.gguf b/Lumian-VLR-7B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..cf13091 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fcf473ff3feeb12fd5757d61d3ff81070076f541459c65def73febfd283fcd7 +size 3492369152 diff --git a/Lumian-VLR-7B-Thinking.Q4_K_M.gguf b/Lumian-VLR-7B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..89c127f --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210285f652b487403480d205cd5a6ca3e90d628cb40ccce448b89be2c8425b56 +size 4683074304 diff --git a/Lumian-VLR-7B-Thinking.Q4_K_S.gguf b/Lumian-VLR-7B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..22e177b --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db6a27261cfe1873ce4c49bc43c8403dc898ab9cdcbd36e9f52ebdf9226f6aa +size 4457769728 diff --git a/Lumian-VLR-7B-Thinking.Q5_K_M.gguf b/Lumian-VLR-7B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..fc51385 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7feb991549e72d3ab22a72f9908cee032c3e169a14e377331d571e3391f703 +size 5444832000 diff --git a/Lumian-VLR-7B-Thinking.Q5_K_S.gguf b/Lumian-VLR-7B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..bc562a7 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a569628f77b36229cd9a98423bf1a93cfbea262b44990a4e59c05835a48c3d5 +size 5315177216 diff --git a/Lumian-VLR-7B-Thinking.Q6_K.gguf b/Lumian-VLR-7B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..d777e14 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588c12335da0e5bb752c04703015dae37e7858f5d72409483ea440e3d5fbd7e4 +size 6254199552 diff --git a/Lumian-VLR-7B-Thinking.Q8_0.gguf b/Lumian-VLR-7B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..8c807ba --- /dev/null +++ b/Lumian-VLR-7B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a4ad1150a204452c3669f003b6fcf26ba1701752317068cef41586c4b812f5 +size 8098525952 diff --git a/Lumian-VLR-7B-Thinking.f16.gguf b/Lumian-VLR-7B-Thinking.f16.gguf new file mode 100644 index 0000000..969e134 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd4334f4435791762720098996dc1df617f8014d08f996077e971a42f58f34d +size 15237853952 diff --git a/Lumian-VLR-7B-Thinking.mmproj-Q8_0.gguf b/Lumian-VLR-7B-Thinking.mmproj-Q8_0.gguf new file mode 100644 index 0000000..0903207 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f5aee35fc002631b65a31af8b2e8af73392b2a4b7d39a869416598cc2054528 +size 853120320 diff --git a/Lumian-VLR-7B-Thinking.mmproj-f16.gguf b/Lumian-VLR-7B-Thinking.mmproj-f16.gguf new file mode 100644 index 0000000..c964792 --- /dev/null +++ b/Lumian-VLR-7B-Thinking.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdd65d2daf4d40f4f84482c224c773ae02c1b62f3f827cf53bd848dc55f8a7c +size 1354163520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c666a8 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: prithivMLmods/Lumian-VLR-7B-Thinking +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- trl +- ocr +- vision-language +- reasoning +- grounded-visual-reasoning +- sft +- grpo +- thinking +- code +- thinking=1 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/Lumian-VLR-7B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Lumian-VLR-7B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-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/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Lumian-VLR-7B-Thinking-GGUF/resolve/main/Lumian-VLR-7B-Thinking.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. + +