commit 4280b76eb125c2cfc981258169e983ba4802155f Author: ModelHub XC Date: Thu Oct 8 01:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-guanaco-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..23b6d28 --- /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 +TinyLlama-guanaco.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-guanaco.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..41ac9e0 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Munia-ak/TinyLlama-guanaco +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Munia-ak/TinyLlama-guanaco + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-guanaco-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/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-guanaco-GGUF/resolve/main/TinyLlama-guanaco.f16.gguf) | f16 | 2.3 | 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. + + diff --git a/TinyLlama-guanaco.IQ4_XS.gguf b/TinyLlama-guanaco.IQ4_XS.gguf new file mode 100644 index 0000000..8b5f275 --- /dev/null +++ b/TinyLlama-guanaco.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff4205e73bb70eef3cf80d2193a4c4d56e0f4020df3088b37dc0945c06a93d32 +size 609808192 diff --git a/TinyLlama-guanaco.Q2_K.gguf b/TinyLlama-guanaco.Q2_K.gguf new file mode 100644 index 0000000..a2bf1bc --- /dev/null +++ b/TinyLlama-guanaco.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973b45301e422f2880e55986abe194bf9f7efefb2882a684d1d23cedc4963b75 +size 432131904 diff --git a/TinyLlama-guanaco.Q3_K_L.gguf b/TinyLlama-guanaco.Q3_K_L.gguf new file mode 100644 index 0000000..7458dfd --- /dev/null +++ b/TinyLlama-guanaco.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455d77802653efb23b68e2953610cd108b250fab946765e0cb5f0010ffa2e0f2 +size 591527744 diff --git a/TinyLlama-guanaco.Q3_K_M.gguf b/TinyLlama-guanaco.Q3_K_M.gguf new file mode 100644 index 0000000..1653b54 --- /dev/null +++ b/TinyLlama-guanaco.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9516d64db9c85ab3d949781b855acfc48428edca97d9f483882ff860b4f1c49 +size 548405056 diff --git a/TinyLlama-guanaco.Q3_K_S.gguf b/TinyLlama-guanaco.Q3_K_S.gguf new file mode 100644 index 0000000..84cc6a1 --- /dev/null +++ b/TinyLlama-guanaco.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:911497cf736e2b3ebfea793102585bbd4eb78afbff391c82582b3af8d042513b +size 499343168 diff --git a/TinyLlama-guanaco.Q4_K_M.gguf b/TinyLlama-guanaco.Q4_K_M.gguf new file mode 100644 index 0000000..838e24c --- /dev/null +++ b/TinyLlama-guanaco.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b721ba7b36bdeb3ce68c3ab5ace090072f10e7199641749d3d64099f4fb7a4a +size 667815744 diff --git a/TinyLlama-guanaco.Q4_K_S.gguf b/TinyLlama-guanaco.Q4_K_S.gguf new file mode 100644 index 0000000..52f408a --- /dev/null +++ b/TinyLlama-guanaco.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6a6422c65e23434ea0a3aaf487285cce7d64382ab8c74bc98ffa3b3ddd88ee +size 639872832 diff --git a/TinyLlama-guanaco.Q5_K_M.gguf b/TinyLlama-guanaco.Q5_K_M.gguf new file mode 100644 index 0000000..aa5e307 --- /dev/null +++ b/TinyLlama-guanaco.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0b76ecc507646a9c177dbebbce57fbfffd160307a8781b580ea5fb9556f472 +size 782044992 diff --git a/TinyLlama-guanaco.Q5_K_S.gguf b/TinyLlama-guanaco.Q5_K_S.gguf new file mode 100644 index 0000000..80c20b3 --- /dev/null +++ b/TinyLlama-guanaco.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739eb1debd0dbae5ea0b22b6b20e85712882508e7841d4a05f11ed1464dcf71e +size 766029632 diff --git a/TinyLlama-guanaco.Q6_K.gguf b/TinyLlama-guanaco.Q6_K.gguf new file mode 100644 index 0000000..be44cae --- /dev/null +++ b/TinyLlama-guanaco.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40c1c0c4d0be07f893984a6c0cc8ca6049e8b2004e66ceff8f5fa2c234e591c +size 903413568 diff --git a/TinyLlama-guanaco.Q8_0.gguf b/TinyLlama-guanaco.Q8_0.gguf new file mode 100644 index 0000000..d9300f6 --- /dev/null +++ b/TinyLlama-guanaco.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596e5b8924b9adb01afff984334c82f49d95942485fe8cd8d59446a398a3a74b +size 1169809216 diff --git a/TinyLlama-guanaco.f16.gguf b/TinyLlama-guanaco.f16.gguf new file mode 100644 index 0000000..0ada23e --- /dev/null +++ b/TinyLlama-guanaco.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264186b6f5e6404eb6f6244823260288cab7f28f54a7e06f451eb3fd6a8dd1f9 +size 2201018176