commit 377fa95458ee987d51bd28bcb1418a22043915d7 Author: ModelHub XC Date: Mon Sep 14 08:34:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: hfl/chinese-llama-2-13b-16k-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..93b2356 --- /dev/null +++ b/README.md @@ -0,0 +1,36 @@ +--- +license: apache-2.0 +language: +- zh +- en +--- + +# Chinese-LLaMA-2-13B-16K-GGUF + +This repository contains the GGUF-v3 models (llama.cpp compatible) for **Chinese-LLaMA-2-13B-16K**. + + +## Performance + +Metric: PPL, lower is better + +| Quant | original | imatrix (`-im`) | +|-----|------|------| +| Q2_K | 11.8958 +/- 0.20739 | 13.0017 +/- 0.23003 | +| Q3_K | 9.7130 +/- 0.17037 | 9.3443 +/- 0.16582 | +| Q4_0 | 9.2002 +/- 0.16219 | - | +| Q4_K | 9.0055 +/- 0.15918 | 8.9848 +/- 0.15908 | +| Q5_0 | 8.8441 +/- 0.15690 | - | +| Q5_K | 8.8999 +/- 0.15751 | 8.8983 +/- 0.15753 | +| Q6_K | 8.8944 +/- 0.15776 | 8.8833 +/- 0.15760 | +| Q8_0 | 8.8745 +/- 0.15745 | - | +| F16 | 8.8687 +/- 0.15729 | - | + +*The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).* + + +## Others + +For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-13b-16k + +Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details. \ 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..5525937 --- /dev/null +++ b/ggml-model-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f557afad954293617f503d38a72ce034725728e423fb74d16e385abc5d559fd +size 26510913344 diff --git a/ggml-model-q2_k-im.gguf b/ggml-model-q2_k-im.gguf new file mode 100644 index 0000000..093e844 --- /dev/null +++ b/ggml-model-q2_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b685465bec6585e2cc5d13c59f5d3c1a15808b26ce77c07d0f779736f1e5cf9a +size 4991758208 diff --git a/ggml-model-q2_k.gguf b/ggml-model-q2_k.gguf new file mode 100644 index 0000000..9e43dac --- /dev/null +++ b/ggml-model-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24b09a19024afb411865e8b8f85456fe8bd417e7a3a6054115e7058ce19c9c8 +size 5566836512 diff --git a/ggml-model-q3_k-im.gguf b/ggml-model-q3_k-im.gguf new file mode 100644 index 0000000..013d052 --- /dev/null +++ b/ggml-model-q3_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e377b630de27fc8efa8549f2c896544e9f7db9bf061330920c1d5ce016a8f62 +size 6487371648 diff --git a/ggml-model-q3_k.gguf b/ggml-model-q3_k.gguf new file mode 100644 index 0000000..4700f08 --- /dev/null +++ b/ggml-model-q3_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cec448193f3c4821b3c4b38782f75ef4061ebfbbbb7d8c140ed427ad3276fc7 +size 6487371552 diff --git a/ggml-model-q4_0.gguf b/ggml-model-q4_0.gguf new file mode 100644 index 0000000..47c3fe7 --- /dev/null +++ b/ggml-model-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6214a80cf177aa8fcd3af5a6d517fe8ab942fd48d2eb83fe1ff4e598ff5a03f8 +size 7531278112 diff --git a/ggml-model-q4_k-im.gguf b/ggml-model-q4_k-im.gguf new file mode 100644 index 0000000..6a460f9 --- /dev/null +++ b/ggml-model-q4_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36c80a23f1a10f418d1e74dc4252d817f705e738d05e3fca9a7a133e31e4c7e +size 8031399808 diff --git a/ggml-model-q4_k.gguf b/ggml-model-q4_k.gguf new file mode 100644 index 0000000..43b20e9 --- /dev/null +++ b/ggml-model-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c3c4f4542820b3487263a83421cbc4bd845e138cf3ff7b337551e44a40ee18 +size 8031399712 diff --git a/ggml-model-q5_0.gguf b/ggml-model-q5_0.gguf new file mode 100644 index 0000000..e48d584 --- /dev/null +++ b/ggml-model-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc25cf32a2514ef122e851552d977c9cf66a494a7a21ceed184675a3f878f0a +size 9152638752 diff --git a/ggml-model-q5_k-im.gguf b/ggml-model-q5_k-im.gguf new file mode 100644 index 0000000..5fbb3d8 --- /dev/null +++ b/ggml-model-q5_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc7209d7549233f08ce6076da8b44dbf02e2dc7b251591f0d727d6fd63617c0 +size 9410277248 diff --git a/ggml-model-q5_k.gguf b/ggml-model-q5_k.gguf new file mode 100644 index 0000000..46e160e --- /dev/null +++ b/ggml-model-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251b3d6df29c5cb5bec1715b03043898353ae68de1591e02456430124df2dc91 +size 9410277152 diff --git a/ggml-model-q6_k-im.gguf b/ggml-model-q6_k-im.gguf new file mode 100644 index 0000000..87e2b03 --- /dev/null +++ b/ggml-model-q6_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b11a0d1465aabc7253fdc50b850c999678ab7230dd1d6048b0973e8376db692f +size 10875334528 diff --git a/ggml-model-q6_k.gguf b/ggml-model-q6_k.gguf new file mode 100644 index 0000000..12b93f4 --- /dev/null +++ b/ggml-model-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af08ca2266e8a0d44eb331c22486b413432229582a628e56b5128b2211426113 +size 10875334432 diff --git a/ggml-model-q8_0.gguf b/ggml-model-q8_0.gguf new file mode 100644 index 0000000..3c73904 --- /dev/null +++ b/ggml-model-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c2d223e9460571ca8e9b2786b03143aa8a1711e95002a07b0562e16f774d234 +size 14085287712