commit 7901bff024d43b0556065128d2ab24bc9f827b53 Author: ModelHub XC Date: Thu Jul 30 06:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..122d284 --- /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 +Llama-3-Taiwan-8B-Instruct-128k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Taiwan-8B-Instruct-128k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Taiwan-8B-Instruct-128k.IQ4_XS.gguf b/Llama-3-Taiwan-8B-Instruct-128k.IQ4_XS.gguf new file mode 100644 index 0000000..63235c8 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34260161c709a1f5faba9540ea490679802e43869e520b1f58d66ad598326181 +size 4484374912 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q2_K.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q2_K.gguf new file mode 100644 index 0000000..46f590e --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57dc110e5060404be37be5465ee0ac2910952cd492fe8f0ddd55cde9efc16e75 +size 3179141888 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_L.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_L.gguf new file mode 100644 index 0000000..7d0445d --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861dd9eae7acedfbcfbc51e6e3060d2e8a75f48636af2d5657a0e8636d55874b +size 4321967680 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_M.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_M.gguf new file mode 100644 index 0000000..5e04b80 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d275863c5025c6247cf9676eb4c3d42bec0acd69902e6f312ec1e59eef6c0e +size 4018929216 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_S.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_S.gguf new file mode 100644 index 0000000..c39c4f6 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe7686e9d7767f84b27a775d270566203aeb4f9ae8e6f8ac53c90170c2963c7 +size 3664510528 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_M.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_M.gguf new file mode 100644 index 0000000..a06d39f --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c97573b6e6eee4e71b5354e4a85a0e2f446e2ab3b1ab6d90c59d4a7d21cb001 +size 4920746624 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_S.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_S.gguf new file mode 100644 index 0000000..23e67d4 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a114bc876b24b51e081e58d7616875a2ac1c04827f0d619cd747bbb3474e0073 +size 4692681344 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_M.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_M.gguf new file mode 100644 index 0000000..57e7d90 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdfae53a91f3143dd05f8d4b2be1cd1ccb97a48d6d06c55230e1ae17cee964a +size 5733000832 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_S.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_S.gguf new file mode 100644 index 0000000..8ab9ff3 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407cc0c9afae104fb3bd200032572789382de9ca4766f88f5d8efc1e4b911ad6 +size 5599307392 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q6_K.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q6_K.gguf new file mode 100644 index 0000000..e224b67 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33359660584b3da604631baf24eefa47ba406baca9f0c851b71f992e631df629 +size 6596020928 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.Q8_0.gguf b/Llama-3-Taiwan-8B-Instruct-128k.Q8_0.gguf new file mode 100644 index 0000000..b63c49a --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c36c32ab4327aeb58882092299f762a3244c84b0d65291c977e2023c53faba +size 8540789312 diff --git a/Llama-3-Taiwan-8B-Instruct-128k.f16.gguf b/Llama-3-Taiwan-8B-Instruct-128k.f16.gguf new file mode 100644 index 0000000..df5fdb0 --- /dev/null +++ b/Llama-3-Taiwan-8B-Instruct-128k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cf155ac5c789560214c626dbbcf155900e5499bfa249b21639588e77b13141 +size 16068924992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0266159 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: yentinglin/Llama-3-Taiwan-8B-Instruct-128k +language: +- zh +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- zhtw +--- +## About + + + + + + +static quants of https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-128k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-Taiwan-8B-Instruct-128k-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-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/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Taiwan-8B-Instruct-128k-GGUF/resolve/main/Llama-3-Taiwan-8B-Instruct-128k.f16.gguf) | f16 | 16.2 | 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. + +