commit c8940fc3cfb0975859f578277d0ae6d3bc97a1a7 Author: ModelHub XC Date: Wed Jun 3 13:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-Chinese-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c8eda5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-Chinese-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Chinese-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-Chinese-8B-Instruct.IQ4_XS.gguf b/Llama3-Chinese-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..1a0a19c --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e46ed18be5b532e283424b78e0533aaf023529862bb8c8959a377933042a865 +size 4484363232 diff --git a/Llama3-Chinese-8B-Instruct.Q2_K.gguf b/Llama3-Chinese-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..93b3e01 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:792751abe707b22904410c81e2e51c95dd1e39f2d9a73cb51502b8949cb95574 +size 3179131872 diff --git a/Llama3-Chinese-8B-Instruct.Q3_K_L.gguf b/Llama3-Chinese-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..99a79de --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d467b52afb78f756bcd11c3f50270a30428c1e50ec457868184c860014f61636 +size 4321956832 diff --git a/Llama3-Chinese-8B-Instruct.Q3_K_M.gguf b/Llama3-Chinese-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b76bcfd --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a4d364d42bab751a1b2dc81fd9aa6befe2bf37abf50725d1db9f3e855af508 +size 4018918368 diff --git a/Llama3-Chinese-8B-Instruct.Q3_K_S.gguf b/Llama3-Chinese-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..1599438 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87fd098d124eae11e7de5258fe538d30f2b3cca931fc563c5bab50e1057c2a31 +size 3664499680 diff --git a/Llama3-Chinese-8B-Instruct.Q4_K_M.gguf b/Llama3-Chinese-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..8edb4c2 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:684be6821bfc8ca47010fe6449eb37531c37af4706a10a7613c073712a1b9df6 +size 4920734688 diff --git a/Llama3-Chinese-8B-Instruct.Q4_K_S.gguf b/Llama3-Chinese-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..ac2e0d9 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3f3839ba39d3eba9c5e80358015c6f9cc87d52f068d203c4914457745d21e2 +size 4692669408 diff --git a/Llama3-Chinese-8B-Instruct.Q5_K_M.gguf b/Llama3-Chinese-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..c837d1c --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5824a314f7982dfead5d60c586c927a4ad3d6ff6fa14830648389691874d87 +size 5732987872 diff --git a/Llama3-Chinese-8B-Instruct.Q5_K_S.gguf b/Llama3-Chinese-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..1e54ff4 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f6c26b061372170409e70021fa9b28b4ce88116f2ca6d5015ffdbfdcff59df +size 5599294432 diff --git a/Llama3-Chinese-8B-Instruct.Q6_K.gguf b/Llama3-Chinese-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..938c6a5 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1724454a0920639b81494f4464e4e8509086fac9bec334cd8e42fb99826c9d25 +size 6596006880 diff --git a/Llama3-Chinese-8B-Instruct.Q8_0.gguf b/Llama3-Chinese-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..9b1ab73 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9aa1e68d0bb622d71c3721c48dd005df22c81d7ae82f9a5cc07a39b4a5e825c +size 8540771296 diff --git a/Llama3-Chinese-8B-Instruct.f16.gguf b/Llama3-Chinese-8B-Instruct.f16.gguf new file mode 100644 index 0000000..00c48a9 --- /dev/null +++ b/Llama3-Chinese-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c64a1acb3f26840e098c171ad66f4af1e1b3fe971204c3c49eae8290921e95 +size 16068891616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f881b0f --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: FlagAlpha/Llama3-Chinese-8B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama3 +- chinese +--- +## About + + + + + + +static quants of https://huggingface.co/FlagAlpha/Llama3-Chinese-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-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/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Chinese-8B-Instruct-GGUF/resolve/main/Llama3-Chinese-8B-Instruct.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. + +