commit 8430236828619156c8452c6d4be0577b9105249a Author: ModelHub XC Date: Wed May 27 15:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lumian2-VLR-7B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7acf94f --- /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 +Lumian2-VLR-7B-Thinking.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lumian2-VLR-7B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lumian2-VLR-7B-Thinking.IQ4_XS.gguf b/Lumian2-VLR-7B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..7b036cf --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8cae2755cd360bd40333154675590998af1d7a7e124c24aa9919bca89e1007 +size 4250299136 diff --git a/Lumian2-VLR-7B-Thinking.Q2_K.gguf b/Lumian2-VLR-7B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..c88c97a --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c8d42bf5c65add8cf0bf10b6fbb0be8c4f26df248f7e02dc3a3008c3a029f7 +size 3015940864 diff --git a/Lumian2-VLR-7B-Thinking.Q3_K_L.gguf b/Lumian2-VLR-7B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..9414941 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5987abeb64dc1531a8fc1f2e3b5a050fac48f30abcf362dc2ef76fb4ad07a8 +size 4088460032 diff --git a/Lumian2-VLR-7B-Thinking.Q3_K_M.gguf b/Lumian2-VLR-7B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..e232499 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f805a418dab197587425c512af892d8a50acb70af6d7127581770d8298a542f +size 3808391936 diff --git a/Lumian2-VLR-7B-Thinking.Q3_K_S.gguf b/Lumian2-VLR-7B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..379f620 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4f8fbb7a60b47ee02f8468342bc14af373669753a0c1654c1ce7de2a236428 +size 3492369152 diff --git a/Lumian2-VLR-7B-Thinking.Q4_K_M.gguf b/Lumian2-VLR-7B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..1b1462e --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f92fe332a44addeda0a845ed18b4328ad77dac312f466d7e5fd6e22a5865593a +size 4683074304 diff --git a/Lumian2-VLR-7B-Thinking.Q4_K_S.gguf b/Lumian2-VLR-7B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..4bf8c47 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9ff125823ed01b12007494d6d3b779806d62455674da021cf6128c35508468 +size 4457769728 diff --git a/Lumian2-VLR-7B-Thinking.Q5_K_M.gguf b/Lumian2-VLR-7B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..003e127 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52cd443f60d7b3f7f5edf84b9dcf844d22653ae44dc45ab5c7e1eae2b839f517 +size 5444832000 diff --git a/Lumian2-VLR-7B-Thinking.Q5_K_S.gguf b/Lumian2-VLR-7B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..8cd962b --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c66c0ed0de42db61651033cff1d659c2c9fcc1369fd7b84aac83334e9bce49c +size 5315177216 diff --git a/Lumian2-VLR-7B-Thinking.Q6_K.gguf b/Lumian2-VLR-7B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..0c82cae --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc19bb2a25509336fd1f9e62b4155678c370a6c7a14e96c883384b6ca9f155c +size 6254199552 diff --git a/Lumian2-VLR-7B-Thinking.Q8_0.gguf b/Lumian2-VLR-7B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..677e114 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b0fcf2c2843c0c269cdc1d116bf7e1c6704f9ca437885ae0f6cba1cec113c7f +size 8098525952 diff --git a/Lumian2-VLR-7B-Thinking.f16.gguf b/Lumian2-VLR-7B-Thinking.f16.gguf new file mode 100644 index 0000000..5081e96 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79381a6cf86c57108dfcad10d75a0e8d4a488dab7f2825eee5e247f5f82a357 +size 15237853952 diff --git a/Lumian2-VLR-7B-Thinking.mmproj-Q8_0.gguf b/Lumian2-VLR-7B-Thinking.mmproj-Q8_0.gguf new file mode 100644 index 0000000..5539191 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438583cc3917c3803cf9af23600eb96e0d3fef59ff146e8964a888448b0b9d8f +size 853120352 diff --git a/Lumian2-VLR-7B-Thinking.mmproj-f16.gguf b/Lumian2-VLR-7B-Thinking.mmproj-f16.gguf new file mode 100644 index 0000000..320d3d7 --- /dev/null +++ b/Lumian2-VLR-7B-Thinking.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8e240d85d31d5a6eeceefff39857a657154c2695ac940bd2c8a48a08362fe3 +size 1354163552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be7a9c7 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: prithivMLmods/Lumian2-VLR-7B-Thinking +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- trl +- thinking +- vlr +- ocr +- vision-language +- reasoning +- grounded-visual-reasoning +- sft +- grpo +- code +- thinking=1 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/Lumian2-VLR-7B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Lumian2-VLR-7B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Lumian2-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/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-VLR-7B-Thinking.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Lumian2-VLR-7B-Thinking-GGUF/resolve/main/Lumian2-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. + +