commit 4f7c50278d7a9dce7bd285e88b2450bba0bb88dd Author: ModelHub XC Date: Mon Sep 21 12:50:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llava-1.1B-20B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9088676 --- /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 +llava-1.1B-20B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.1B-20B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..574ae32 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: snoop2head/llava-1.1B-20B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/snoop2head/llava-1.1B-20B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llava-1.1B-20B-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/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llava-1.1B-20B-GGUF/resolve/main/llava-1.1B-20B.f16.gguf) | f16 | 1.7 | 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. + + diff --git a/llava-1.1B-20B.IQ4_XS.gguf b/llava-1.1B-20B.IQ4_XS.gguf new file mode 100644 index 0000000..2a0e01a --- /dev/null +++ b/llava-1.1B-20B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32e597f9166a93f6d375a693ae0f815d2e112299f5f44d8a8fb02e527096e56 +size 431392192 diff --git a/llava-1.1B-20B.Q2_K.gguf b/llava-1.1B-20B.Q2_K.gguf new file mode 100644 index 0000000..c9f3d0c --- /dev/null +++ b/llava-1.1B-20B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f987c5574a12a66bad928e87a10d10b7e3ceaefbc6c9c67e23aa6b98e914e7 +size 307277248 diff --git a/llava-1.1B-20B.Q3_K_L.gguf b/llava-1.1B-20B.Q3_K_L.gguf new file mode 100644 index 0000000..b2f9d0e --- /dev/null +++ b/llava-1.1B-20B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433c385d23e1a02ee53795c13675030d9e47e31ca583806b361844f6b9ec8b40 +size 422566336 diff --git a/llava-1.1B-20B.Q3_K_M.gguf b/llava-1.1B-20B.Q3_K_M.gguf new file mode 100644 index 0000000..edd0657 --- /dev/null +++ b/llava-1.1B-20B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d6492586593b4594be19a8b34cbbbe7862f661a732f7b74d5780f30ee708bd +size 390912448 diff --git a/llava-1.1B-20B.Q3_K_S.gguf b/llava-1.1B-20B.Q3_K_S.gguf new file mode 100644 index 0000000..99b4ccb --- /dev/null +++ b/llava-1.1B-20B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d739897ed0532034eaa1b7a5adb6f34b5e748c89240532a20bc1f0789a067b36 +size 354441664 diff --git a/llava-1.1B-20B.Q4_K_M.gguf b/llava-1.1B-20B.Q4_K_M.gguf new file mode 100644 index 0000000..7e5a870 --- /dev/null +++ b/llava-1.1B-20B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bd3bbe48821c2b2d8776a4c35f028fc8e108bb35cdd7773e920ea63db84bea +size 477976000 diff --git a/llava-1.1B-20B.Q4_K_S.gguf b/llava-1.1B-20B.Q4_K_S.gguf new file mode 100644 index 0000000..e6c0951 --- /dev/null +++ b/llava-1.1B-20B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84383988e2e819b1befa9217313f2a37202f7190f6ea74d3e69e9861dfab5564 +size 454751680 diff --git a/llava-1.1B-20B.Q5_K_M.gguf b/llava-1.1B-20B.Q5_K_M.gguf new file mode 100644 index 0000000..55f2357 --- /dev/null +++ b/llava-1.1B-20B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9744198352d7cfb985508c09eaeabd6657e4f97c74fba007ba9349b32e6fd0 +size 556078528 diff --git a/llava-1.1B-20B.Q5_K_S.gguf b/llava-1.1B-20B.Q5_K_S.gguf new file mode 100644 index 0000000..af5d74d --- /dev/null +++ b/llava-1.1B-20B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c8623abc2c7707622221d6c8628dc14011087af9eb85e6d952cc3ed1ea5145 +size 542291392 diff --git a/llava-1.1B-20B.Q6_K.gguf b/llava-1.1B-20B.Q6_K.gguf new file mode 100644 index 0000000..adb2197 --- /dev/null +++ b/llava-1.1B-20B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441677554c4815a3bbce57c0b2c8b5a1cd6ad879998f93f3ec8cd533eb0297e9 +size 639062464 diff --git a/llava-1.1B-20B.Q8_0.gguf b/llava-1.1B-20B.Q8_0.gguf new file mode 100644 index 0000000..4d9ab65 --- /dev/null +++ b/llava-1.1B-20B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f22e6c16b1b7556cb6d750e5fef747a9ffef6f639658339f29e3a7fdf8c4c9 +size 827431360 diff --git a/llava-1.1B-20B.f16.gguf b/llava-1.1B-20B.f16.gguf new file mode 100644 index 0000000..85c1dc3 --- /dev/null +++ b/llava-1.1B-20B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9dc3300f0178660beb8043390ee101e0f400b57db8ef0e0cfc13a1cb49317c8 +size 1556601280