commit 28c49f8b67157698236c77a01ac19ff8bc9b1b9e Author: ModelHub XC Date: Fri Sep 11 20:52:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: hfl/llama-3-chinese-8b-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..dcf89b2 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +license: apache-2.0 +language: +- zh +- en +--- + +# Llama-3-Chinese-8B-GGUF + +

+ +

+ +This repository contains **Llama-3-Chinese-8B-GGUF** (llama.cpp/ollama/tgw, etc. compatible), which is the quantized version of [Llama-3-Chinese-8B](https://huggingface.co/hfl/llama-3-chinese-8b). + +**Note: this is a foundation model, which is not suitable for conversation, QA, etc.** + +Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 + +## Performance + +Metric: PPL, **lower is better** + +*Note: Old models have been removed due to its inferior performance.* + +| Quant | Size | PPL (old model) | 👍🏻 PPL (new model) | +| :---: | -------: | ------------------: | ------------------: | +| Q2_K | 2.96 GB | 17.7212 +/- 0.59814 | 11.8595 +/- 0.20061 | +| Q3_K | 3.74 GB | 8.6303 +/- 0.28481 | 5.7559 +/- 0.09152 | +| Q4_0 | 4.34 GB | 8.2513 +/- 0.27102 | 5.5495 +/- 0.08832 | +| Q4_K | 4.58 GB | 7.8897 +/- 0.25830 | 5.3126 +/- 0.08500 | +| Q5_0 | 5.21 GB | 7.7975 +/- 0.25639 | 5.2222 +/- 0.08317 | +| Q5_K | 5.34 GB | 7.7062 +/- 0.25218 | 5.1813 +/- 0.08264 | +| Q6_K | 6.14 GB | 7.6600 +/- 0.25043 | 5.1481 +/- 0.08205 | +| Q8_0 | 7.95 GB | 7.6512 +/- 0.25064 | 5.1350 +/- 0.08190 | +| F16 | 14.97 GB | 7.6389 +/- 0.25001 | 5.1302 +/- 0.08184 | + + +## Others + +- For full model, please see: https://huggingface.co/hfl/llama-3-chinese-8b + +- For LoRA-only model, please see: https://huggingface.co/hfl/llama-3-chinese-8b-lora + +- If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/ggml-model-f16.gguf b/ggml-model-f16.gguf new file mode 100644 index 0000000..cb0bf62 --- /dev/null +++ b/ggml-model-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae38d05b676c08ba1b422769fbb3d5206d5f60dad9cfbb753efe8f18540081ca +size 16068890432 diff --git a/ggml-model-q2_k.gguf b/ggml-model-q2_k.gguf new file mode 100644 index 0000000..6ec3b51 --- /dev/null +++ b/ggml-model-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405c81fce3f2ea2f9127635a2e42902887db7ab887247ee34980f869e15b70e2 +size 3179130720 diff --git a/ggml-model-q3_k.gguf b/ggml-model-q3_k.gguf new file mode 100644 index 0000000..e0bb4d6 --- /dev/null +++ b/ggml-model-q3_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221ff0298644cbe4624519944f10b66963d16a309fd7c125380a8b7b7ca96150 +size 4018917216 diff --git a/ggml-model-q4_0.gguf b/ggml-model-q4_0.gguf new file mode 100644 index 0000000..3baa7ae --- /dev/null +++ b/ggml-model-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d21960dc94aa421728f470262c716965d9a94a8734152fca7f6f9d8ebaf9a81 +size 4661210976 diff --git a/ggml-model-q4_k.gguf b/ggml-model-q4_k.gguf new file mode 100644 index 0000000..11b3831 --- /dev/null +++ b/ggml-model-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea2740a1f02b0f1f006de70ada17e5d27e6dc8525a1c433a71bf7c61f864394 +size 4920733536 diff --git a/ggml-model-q5_0.gguf b/ggml-model-q5_0.gguf new file mode 100644 index 0000000..e3763aa --- /dev/null +++ b/ggml-model-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e98af9d1003262f2f38e3a780d3cbb84d8cec071f428f74f07b5a13ed105fe +size 5599293280 diff --git a/ggml-model-q5_k.gguf b/ggml-model-q5_k.gguf new file mode 100644 index 0000000..6079f63 --- /dev/null +++ b/ggml-model-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8583ecc97337db5ae30f7914514245a6c1c7cfc0242659f72df816f9b9a98b +size 5732986720 diff --git a/ggml-model-q6_k.gguf b/ggml-model-q6_k.gguf new file mode 100644 index 0000000..fee6c7d --- /dev/null +++ b/ggml-model-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1331c415761089fb2802f0fffa1918d3927b82a24fddb6de47568a42300909 +size 6596005728 diff --git a/ggml-model-q8_0.gguf b/ggml-model-q8_0.gguf new file mode 100644 index 0000000..c2d5854 --- /dev/null +++ b/ggml-model-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee7939eb39f8eb7c31d9ea2e3a712b7e95fb25171affd77ff06b1b5a5c7c870 +size 8540770144