commit f200c5e9a11ed88e10d59bf8201433bc58fe218c Author: ModelHub XC Date: Sun May 24 17:19:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llava-1.5-13b-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f8117fb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-1.5-13b-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-1.5-13b-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f3d96ea --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +arxiv: 2304.08485 +base_model: llava-hf/llava-1.5-13b-hf +language: +- en +library_name: transformers +license: llama2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- vision +- image-text-to-text +--- +## About + + + + + + +static quants of https://huggingface.co/llava-hf/llava-1.5-13b-hf + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llava-1.5-13b-hf-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llava-1.5-13b-hf-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/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q2_K.gguf) | Q2_K | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q3_K_S.gguf) | Q3_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q3_K_L.gguf) | Q3_K_L | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.IQ4_XS.gguf) | IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q5_K_S.gguf) | Q5_K_S | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q5_K_M.gguf) | Q5_K_M | 9.3 | | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q6_K.gguf) | Q6_K | 10.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llava-1.5-13b-hf-GGUF/resolve/main/llava-1.5-13b-hf.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality | + +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-1.5-13b-hf.IQ4_XS.gguf b/llava-1.5-13b-hf.IQ4_XS.gguf new file mode 100644 index 0000000..98e3142 --- /dev/null +++ b/llava-1.5-13b-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60bb947e8fa8005ec3928b1f1967881cf920c41d0b1ca6f0de2ac71ddcce02fb +size 7019964160 diff --git a/llava-1.5-13b-hf.Q2_K.gguf b/llava-1.5-13b-hf.Q2_K.gguf new file mode 100644 index 0000000..9c5f9e5 --- /dev/null +++ b/llava-1.5-13b-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce55b1b58ee880afa734d2cb842d11699dbe7cda3250e6d2e7ba9ce843401303 +size 4854649600 diff --git a/llava-1.5-13b-hf.Q3_K_L.gguf b/llava-1.5-13b-hf.Q3_K_L.gguf new file mode 100644 index 0000000..aa720eb --- /dev/null +++ b/llava-1.5-13b-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4ec1824106da5ac102a036ba8c2c35b665fa4fe6a3519ab4f77dfe19d23112 +size 6929972480 diff --git a/llava-1.5-13b-hf.Q3_K_M.gguf b/llava-1.5-13b-hf.Q3_K_M.gguf new file mode 100644 index 0000000..d3842c7 --- /dev/null +++ b/llava-1.5-13b-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653ac4537cefcc13d00ec34412ef14b6167ed13f030cb59923d0e88623058201 +size 6338182400 diff --git a/llava-1.5-13b-hf.Q3_K_S.gguf b/llava-1.5-13b-hf.Q3_K_S.gguf new file mode 100644 index 0000000..fa55f2c --- /dev/null +++ b/llava-1.5-13b-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86ccc6658e20b54074d1949b889c3345d22a609c66ddfce5b3af25e351c29aa +size 5659393280 diff --git a/llava-1.5-13b-hf.Q4_K_M.gguf b/llava-1.5-13b-hf.Q4_K_M.gguf new file mode 100644 index 0000000..35c99a1 --- /dev/null +++ b/llava-1.5-13b-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f4d2fc1283550ee504de7b35f83d590b864e58be6e1c0eecad5a72fd813451 +size 7866412800 diff --git a/llava-1.5-13b-hf.Q4_K_S.gguf b/llava-1.5-13b-hf.Q4_K_S.gguf new file mode 100644 index 0000000..be02236 --- /dev/null +++ b/llava-1.5-13b-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed28e2b4f544eb4573c86088f77dfeacc832ef0eabded3ccc6e1c0c213cd040b +size 7423635200 diff --git a/llava-1.5-13b-hf.Q5_K_M.gguf b/llava-1.5-13b-hf.Q5_K_M.gguf new file mode 100644 index 0000000..4547492 --- /dev/null +++ b/llava-1.5-13b-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb607764fc94cd04d1d4c12ad7b4cc04dda9cb1a1714890741d2a5c01043c79b +size 9230421760 diff --git a/llava-1.5-13b-hf.Q5_K_S.gguf b/llava-1.5-13b-hf.Q5_K_S.gguf new file mode 100644 index 0000000..b494d4b --- /dev/null +++ b/llava-1.5-13b-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78172fe718a220d43f7cdc8f32d9ca078503b4aaefec0f8be73cb6ad5b01709a +size 8972783360 diff --git a/llava-1.5-13b-hf.Q6_K.gguf b/llava-1.5-13b-hf.Q6_K.gguf new file mode 100644 index 0000000..22ca2c4 --- /dev/null +++ b/llava-1.5-13b-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c1ea4d805a832ae912ff0d8f29b0b32a3a1faaacf1ee2fb1202f37e37d9885 +size 10679681280 diff --git a/llava-1.5-13b-hf.Q8_0.gguf b/llava-1.5-13b-hf.Q8_0.gguf new file mode 100644 index 0000000..a580bb2 --- /dev/null +++ b/llava-1.5-13b-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389d9c38f3f7805d76b7713b7825e89798b678643ccdb98929200a259e8b9b31 +size 13832019200