commit c1035c3a327f3cc91dc9fc2bcc618bbc65fcbb60 Author: ModelHub XC Date: Sun May 10 00:11:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Oganesson-TinyLlama-1.2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b393bd --- /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 +Oganesson-TinyLlama-1.2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Oganesson-TinyLlama-1.2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Oganesson-TinyLlama-1.2B.IQ4_XS.gguf b/Oganesson-TinyLlama-1.2B.IQ4_XS.gguf new file mode 100644 index 0000000..72339c8 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f74aa829c068e2398134c997980ee43a26134a302024a185937795ab8ed1ea +size 748381568 diff --git a/Oganesson-TinyLlama-1.2B.Q2_K.gguf b/Oganesson-TinyLlama-1.2B.Q2_K.gguf new file mode 100644 index 0000000..c4a9e96 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6a919cc51dc589af3278ebff9d012ca1cf75b1a00768235b9062902402dc03 +size 580871552 diff --git a/Oganesson-TinyLlama-1.2B.Q3_K_L.gguf b/Oganesson-TinyLlama-1.2B.Q3_K_L.gguf new file mode 100644 index 0000000..4f4518c --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4e752e6b56788ba524ae80acbc98b8f456a76f343a5e84f0ada481f7fecf44 +size 732521856 diff --git a/Oganesson-TinyLlama-1.2B.Q3_K_M.gguf b/Oganesson-TinyLlama-1.2B.Q3_K_M.gguf new file mode 100644 index 0000000..f7a9d8d --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846aa3dfd894d81a11f08a350dec6b525e079d62ce66df920acf54e1727f206b +size 690840960 diff --git a/Oganesson-TinyLlama-1.2B.Q3_K_S.gguf b/Oganesson-TinyLlama-1.2B.Q3_K_S.gguf new file mode 100644 index 0000000..ace2317 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:746b3eb35bb96948fc9122721fea8103f3a4025d503ae5d0cfdb0298ce327b50 +size 641688960 diff --git a/Oganesson-TinyLlama-1.2B.Q4_K_M.gguf b/Oganesson-TinyLlama-1.2B.Q4_K_M.gguf new file mode 100644 index 0000000..831457f --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5a4a994cef3cf8ddf2ec681735877ffb00bff0d1d86cdd94194ab9f23e9076 +size 807691648 diff --git a/Oganesson-TinyLlama-1.2B.Q4_K_S.gguf b/Oganesson-TinyLlama-1.2B.Q4_K_S.gguf new file mode 100644 index 0000000..1e6bd5a --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70688223fdb86d2e815c554e0832a27eedb3f4c5eb448cd6a3623a6c3896440d +size 775644544 diff --git a/Oganesson-TinyLlama-1.2B.Q5_K_M.gguf b/Oganesson-TinyLlama-1.2B.Q5_K_M.gguf new file mode 100644 index 0000000..2a7ef63 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59f8b731bd90ae4444d0d43e40832d6351176840c835e595947142aa02aa8aa +size 911500672 diff --git a/Oganesson-TinyLlama-1.2B.Q5_K_S.gguf b/Oganesson-TinyLlama-1.2B.Q5_K_S.gguf new file mode 100644 index 0000000..eda4e41 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc3b193fe501682f50f85330b735c684c88dfefadc841a950812d22c225e5a4 +size 892560768 diff --git a/Oganesson-TinyLlama-1.2B.Q6_K.gguf b/Oganesson-TinyLlama-1.2B.Q6_K.gguf new file mode 100644 index 0000000..4a2c3f7 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f377bd4d88dba1d050074eff9eb73c96f43e10a1680998b5602a233804e4cc +size 1021797760 diff --git a/Oganesson-TinyLlama-1.2B.Q8_0.gguf b/Oganesson-TinyLlama-1.2B.Q8_0.gguf new file mode 100644 index 0000000..42a3c95 --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4cb5680eac428dbfbe952cf5db640e5777dcbe846c3d562885b39fa4de724b4 +size 1321080192 diff --git a/Oganesson-TinyLlama-1.2B.f16.gguf b/Oganesson-TinyLlama-1.2B.f16.gguf new file mode 100644 index 0000000..9bb250d --- /dev/null +++ b/Oganesson-TinyLlama-1.2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42678239b31bc7d921c77216809a47e099e9e66ea1482ef75c83b8496706245b +size 2479592832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..157c0fc --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: prithivMLmods/Oganesson-TinyLlama-1.2B +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- code +- llama-3.2 +- math +- general-purpose +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/Oganesson-TinyLlama-1.2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Oganesson-TinyLlama-1.2B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-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/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Oganesson-TinyLlama-1.2B-GGUF/resolve/main/Oganesson-TinyLlama-1.2B.f16.gguf) | f16 | 2.6 | 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. + +