commit 8f88ac8551ac4c02519470d93f369460b8677153 Author: ModelHub XC Date: Thu Jun 18 10:40:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llava-0.5B-10B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..31925da --- /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-0.5B-10B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llava-0.5B-10B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..424cfd4 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: snoop2head/llava-0.5B-10B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/snoop2head/llava-0.5B-10B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llava-0.5B-10B-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-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llava-0.5B-10B-GGUF/resolve/main/llava-0.5B-10B.f16.gguf) | f16 | 0.8 | 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-0.5B-10B.IQ4_XS.gguf b/llava-0.5B-10B.IQ4_XS.gguf new file mode 100644 index 0000000..41ca7e9 --- /dev/null +++ b/llava-0.5B-10B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed43431ccd1c72fe8d7db66570fe68b3512df44fc7baef83af5825a0c48a2e9 +size 210352576 diff --git a/llava-0.5B-10B.Q2_K.gguf b/llava-0.5B-10B.Q2_K.gguf new file mode 100644 index 0000000..1c01460 --- /dev/null +++ b/llava-0.5B-10B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77cba5980b17e53a4218ceda2d2b7f7dc6a1c2c17e2fd7e94733e0b820cf8d29 +size 151865792 diff --git a/llava-0.5B-10B.Q3_K_L.gguf b/llava-0.5B-10B.Q3_K_L.gguf new file mode 100644 index 0000000..ca5b091 --- /dev/null +++ b/llava-0.5B-10B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0196d1bc892af610e05e92f1341d369bf596b76ce6bde2b7b52e26816376b45c +size 205181376 diff --git a/llava-0.5B-10B.Q3_K_M.gguf b/llava-0.5B-10B.Q3_K_M.gguf new file mode 100644 index 0000000..3061509 --- /dev/null +++ b/llava-0.5B-10B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2245d66aadbaa6c196777061e82e12c1ff94a952b2d4aa67fbe6444dbfd505 +size 190861760 diff --git a/llava-0.5B-10B.Q3_K_S.gguf b/llava-0.5B-10B.Q3_K_S.gguf new file mode 100644 index 0000000..a40df5e --- /dev/null +++ b/llava-0.5B-10B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d7bcb24d4f39877c0a5da6620a66b872110098ddc7781bf45fa81e6fa17e7a +size 174363072 diff --git a/llava-0.5B-10B.Q4_K_M.gguf b/llava-0.5B-10B.Q4_K_M.gguf new file mode 100644 index 0000000..4ccc103 --- /dev/null +++ b/llava-0.5B-10B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234bdd088266ee6c6d5043a3d7784e273ff14e4201f795cab9eb41908e81f1cf +size 231823808 diff --git a/llava-0.5B-10B.Q4_K_S.gguf b/llava-0.5B-10B.Q4_K_S.gguf new file mode 100644 index 0000000..20ec6e8 --- /dev/null +++ b/llava-0.5B-10B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63af9b882948a436fd779e65a21df8d33dce514909551ffe22636a1700ca650d +size 221264320 diff --git a/llava-0.5B-10B.Q5_K_M.gguf b/llava-0.5B-10B.Q5_K_M.gguf new file mode 100644 index 0000000..994474d --- /dev/null +++ b/llava-0.5B-10B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f7326241c3e105d647e66c16be338e8bc9df1de70de2c81decef2cf085c1d7 +size 268556736 diff --git a/llava-0.5B-10B.Q5_K_S.gguf b/llava-0.5B-10B.Q5_K_S.gguf new file mode 100644 index 0000000..6d79b86 --- /dev/null +++ b/llava-0.5B-10B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71887460baa82427b11f74611c90ca10327ec4b6da16cb69cacc9ca7d51f2d8a +size 262289856 diff --git a/llava-0.5B-10B.Q6_K.gguf b/llava-0.5B-10B.Q6_K.gguf new file mode 100644 index 0000000..d82c540 --- /dev/null +++ b/llava-0.5B-10B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1738736d7091f1a1a6fdb54c35629344712b890556b39cf5a01f6018b9f69fab +size 307585472 diff --git a/llava-0.5B-10B.Q8_0.gguf b/llava-0.5B-10B.Q8_0.gguf new file mode 100644 index 0000000..bf2c337 --- /dev/null +++ b/llava-0.5B-10B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087da4c6b03fb6509d61085060dcf35f3996437d534adc602927a0e5cacc5b90 +size 398119360 diff --git a/llava-0.5B-10B.f16.gguf b/llava-0.5B-10B.f16.gguf new file mode 100644 index 0000000..1ef9abb --- /dev/null +++ b/llava-0.5B-10B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff95d6642a57f93b15c166fdde28724f0aa85079287884ff08527b838927594 +size 748573120