commit 6ce80fd79b1646014db2f4b650f98e63ecdbea87 Author: ModelHub XC Date: Sun May 31 06:32:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b19b258 --- /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-1.1B-Chat-guanaco.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-guanaco.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e96be72 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Sebas012/TinyLlama-1.1B-Chat-guanaco +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Sebas012/TinyLlama-1.1B-Chat-guanaco + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-1.1B-Chat-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-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-guanaco.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-guanaco-GGUF/resolve/main/TinyLlama-1.1B-Chat-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-1.1B-Chat-guanaco.IQ4_XS.gguf b/TinyLlama-1.1B-Chat-guanaco.IQ4_XS.gguf new file mode 100644 index 0000000..9898aa1 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b717a12a98c7b571c4b5065351af4fe236d1a9b02289e2df3232e423e2233961 +size 609808224 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q2_K.gguf b/TinyLlama-1.1B-Chat-guanaco.Q2_K.gguf new file mode 100644 index 0000000..642ab80 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f4a8786dc0c51ea79eb52d3b769911dcaa2002663aa56d42258e26271b7ae98 +size 432131936 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q3_K_L.gguf b/TinyLlama-1.1B-Chat-guanaco.Q3_K_L.gguf new file mode 100644 index 0000000..48d79c6 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49550e38f28c6eda5a9f51d96a6c1a611755b0f96303a395897c9f9bb1b630ec +size 591527776 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q3_K_M.gguf b/TinyLlama-1.1B-Chat-guanaco.Q3_K_M.gguf new file mode 100644 index 0000000..4a8257c --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c43dc86594cd4cb91fbaf2c7701f440c4a554071c6b8e447bb4074abad6378 +size 548405088 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q3_K_S.gguf b/TinyLlama-1.1B-Chat-guanaco.Q3_K_S.gguf new file mode 100644 index 0000000..c5299fa --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10107c331ec099d4676556d20b94d4b9aab20f6a66f9a32bab6b803af8762a15 +size 499343200 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q4_K_M.gguf b/TinyLlama-1.1B-Chat-guanaco.Q4_K_M.gguf new file mode 100644 index 0000000..632ecbe --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f44a5418e214910630ad4bfd2ba89035471fe369ed7ebe9d629956492291a33 +size 667815776 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q4_K_S.gguf b/TinyLlama-1.1B-Chat-guanaco.Q4_K_S.gguf new file mode 100644 index 0000000..8e0f80e --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331b4845b320a7bd3f6aedb7aa22cbe5c56ddf86de38526b37543d7fb55eb532 +size 639872864 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q5_K_M.gguf b/TinyLlama-1.1B-Chat-guanaco.Q5_K_M.gguf new file mode 100644 index 0000000..875aa2b --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6379640db5a6cbd26d49be3b7ce7045086044f2e3a3f0e2ebf54fdda954a264f +size 782045024 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q5_K_S.gguf b/TinyLlama-1.1B-Chat-guanaco.Q5_K_S.gguf new file mode 100644 index 0000000..6054bb7 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006a49a1aa709ecfb360544970af7326c90667b47c9c3fbde357f9a4e5601f15 +size 766029664 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q6_K.gguf b/TinyLlama-1.1B-Chat-guanaco.Q6_K.gguf new file mode 100644 index 0000000..b7919f4 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66888e7d73e7822548284e218a7e362d1360a45ec4c9e7dcd50ed411f19a8e3a +size 903413600 diff --git a/TinyLlama-1.1B-Chat-guanaco.Q8_0.gguf b/TinyLlama-1.1B-Chat-guanaco.Q8_0.gguf new file mode 100644 index 0000000..a572692 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac9986d7cf270f7cf781d79a62f8e3d70087265a3a711ca70d4504791e2035e +size 1169809248 diff --git a/TinyLlama-1.1B-Chat-guanaco.f16.gguf b/TinyLlama-1.1B-Chat-guanaco.f16.gguf new file mode 100644 index 0000000..4db8036 --- /dev/null +++ b/TinyLlama-1.1B-Chat-guanaco.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44082bae59bf2430fac1c37a08aa8d9ba50f266ebfd1426595323972a5cc081 +size 2201018208