commit 4d599c44b45dbf0d2ccb7889b80ce92918fdb9c0 Author: ModelHub XC Date: Sat May 9 08:53:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bd2d58f --- /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 +Llama3.2-TaiPhone-1B-Instruct-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-1B-Instruct-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.IQ4_XS.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..afe5a39 --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a61a8d1a50f22330c61a9cff894b6c67c8cfb1afeeccdfbd1b1c37952b9f2e +size 748385664 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q2_K.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..9f90559 --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7019e75118cd66e2376ac4040830659e2d0c47ad68040bb9fcf9b1e8d837a8b8 +size 580875648 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_L.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..56fa577 --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4346dd4ca17f76338dcb384d88ebc4cb2b1848a98a0ad26244752999658832fb +size 732525952 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_M.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..f8547ed --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2b91a61f4e2e53daa0178aa6b37d1d69ab502a4561eae05b6af451787ea72c6 +size 690845056 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_S.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..c52b73c --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b8305dfddf8c80129eedcc8585ffecd62d87c57bc2132c9e96972e0d379ca8 +size 641693056 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_M.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..0b32432 --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853305b50f7eb7eff3533201da3d27372d855ebd2ca42217b7a501c814628ca5 +size 807695744 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_S.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..316894b --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:727da1dc4f83207a9270c77b3cde892e705abd3f014042847d5bea8e2d9d6a26 +size 775648640 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_M.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..714e799 --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9916967e71de3d85ff615a05a0542f5492c4fabb97f68666b23b88b9795aafe +size 911504768 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_S.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..e8aac27 --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3eed64ec4431c8a9075315c69c928fa2d12f6ee8de1e443f07533eeb8bec823 +size 892564864 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q6_K.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..ff64cee --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1ddb037d5ee146b92fe5a7954921ca638139f085937a882050f9633cdb380b +size 1021801856 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q8_0.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..b9afc1d --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6831e4f2facb7494df652acc4dd54443dac6a053c111eb5f7e92fd92ada8b86 +size 1321084288 diff --git a/Llama3.2-TaiPhone-1B-Instruct-v0.1.f16.gguf b/Llama3.2-TaiPhone-1B-Instruct-v0.1.f16.gguf new file mode 100644 index 0000000..2c78fbe --- /dev/null +++ b/Llama3.2-TaiPhone-1B-Instruct-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0211d0ec86c6ce411fcb23a4983e9c0875d78d79bcee7b7874505a5bd431b8 +size 2479596928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..68578f3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: aqweteddy/Llama3.2-TaiPhone-1B-Instruct-v0.1 +language: +- zh +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- slm +- taiwan +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aqweteddy/Llama3.2-TaiPhone-1B-Instruct-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-TaiPhone-1B-Instruct-v0.1-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/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-1B-Instruct-v0.1-GGUF/resolve/main/Llama3.2-TaiPhone-1B-Instruct-v0.1.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. + +