commit 097b30a02a72542f98ebf5c1c023557f8834a0ab Author: ModelHub XC Date: Thu Jun 18 08:28:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: hfl/chinese-llama-2-13b-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..6f80220 --- /dev/null +++ b/README.md @@ -0,0 +1,34 @@ +--- +license: apache-2.0 +--- + +# Chinese-LLaMA-2-13B-GGUF + +This repository contains the GGUF-v3 models (llama.cpp compatible) for **Chinese-LLaMA-2-13B**. + + +## Performance + +Metric: PPL, lower is better + +| Quant | original | imatrix (`-im`) | +|-----|------|------| +| Q2_K | 14.4701 +/- 0.26107 | 17.4275 +/- 0.31909 | +| Q3_K | 10.1620 +/- 0.18277 | 9.7486 +/- 0.17744 | +| Q4_0 | 9.8633 +/- 0.17792 | - | +| Q4_K | 9.2735 +/- 0.16793 | 9.2734 +/- 0.16792 | +| Q5_0 | 9.3553 +/- 0.16945 | - | +| Q5_K | 9.1767 +/- 0.16634 | 9.1594 +/- 0.16590 | +| Q6_K | 9.1326 +/- 0.16546 | 9.1478 +/- 0.16583 | +| Q8_0 | 9.1394 +/- 0.16574 | - | +| F16 | 9.1050 +/- 0.16518 | - | + +*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 + +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/config.json b/config.json new file mode 100644 index 0000000..1e86561 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "_name_or_path": "Llama-2-7b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "auto_map": { + "AutoConfig": "configuration_llama.LlamaConfig", + "AutoModelForCausalLM": "modeling_llama_yarn.LlamaForCausalLM" + }, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 65536, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 16.0, + "finetuned": true, + "original_max_position_embeddings": 4096, + "type": "yarn" + }, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.33.3", + "use_cache": true, + "vocab_size": 55296 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "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..0011d3f --- /dev/null +++ b/ggml-model-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6fbd94d377d1a89fef8f18662a7d48b608037db18bb2e70d79b4d78b4c40c6b +size 26510913248 diff --git a/ggml-model-q2_k-im.gguf b/ggml-model-q2_k-im.gguf new file mode 100644 index 0000000..fd4d897 --- /dev/null +++ b/ggml-model-q2_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:957e07ad355d479289bf2c2510aebe6b64e3f6e2f9a87ed369a3236ac5b961ec +size 4991758112 diff --git a/ggml-model-q2_k.gguf b/ggml-model-q2_k.gguf new file mode 100644 index 0000000..f5f469e --- /dev/null +++ b/ggml-model-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74fd1178c111b949de5026a25a5364bf87c5d46ed4da32d9f7fbd083c5ee1751 +size 5566836416 diff --git a/ggml-model-q3_k-im.gguf b/ggml-model-q3_k-im.gguf new file mode 100644 index 0000000..a600261 --- /dev/null +++ b/ggml-model-q3_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb8ccf19471a164f0b008022cbf99aaf09056947f97b11256ce49dbecfa2c06 +size 6487371552 diff --git a/ggml-model-q3_k.gguf b/ggml-model-q3_k.gguf new file mode 100644 index 0000000..09695cb --- /dev/null +++ b/ggml-model-q3_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4d3f74c83fc14a236e81495bbadc886c87d977b167bbc5081d6e2838aa0109 +size 6487371456 diff --git a/ggml-model-q4_0.gguf b/ggml-model-q4_0.gguf new file mode 100644 index 0000000..6d244f3 --- /dev/null +++ b/ggml-model-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95993c9ec36d284803ea9b1d1a2328fe3a56de13a39c59e7bf0da325ee5db15d +size 7531278016 diff --git a/ggml-model-q4_k-im.gguf b/ggml-model-q4_k-im.gguf new file mode 100644 index 0000000..84ae97f --- /dev/null +++ b/ggml-model-q4_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5ced3d5599a618ad83020f23904fb923b0157ff2edbdbc30941f3372f45c81 +size 8031399712 diff --git a/ggml-model-q4_k.gguf b/ggml-model-q4_k.gguf new file mode 100644 index 0000000..18f010a --- /dev/null +++ b/ggml-model-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a811382f3d21ce18500cf231a87b2eda206765fdec161239a853f4571a6602 +size 8031399616 diff --git a/ggml-model-q5_0.gguf b/ggml-model-q5_0.gguf new file mode 100644 index 0000000..b2191f5 --- /dev/null +++ b/ggml-model-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298619b7dbbb582281aee62de9dbd1ec2c605158cc114e14aad5e0f24c38a93d +size 9152638656 diff --git a/ggml-model-q5_k-im.gguf b/ggml-model-q5_k-im.gguf new file mode 100644 index 0000000..96d3bb2 --- /dev/null +++ b/ggml-model-q5_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c93b01f79f2886a81469c33608cbca09db24dc247c8c269c4b80976316d8120 +size 9410277152 diff --git a/ggml-model-q5_k.gguf b/ggml-model-q5_k.gguf new file mode 100644 index 0000000..0971aeb --- /dev/null +++ b/ggml-model-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7424de30ca58c3a79195ce28714b8b8cf46db783884af34ad30a8709866ac01e +size 9410277056 diff --git a/ggml-model-q6_k-im.gguf b/ggml-model-q6_k-im.gguf new file mode 100644 index 0000000..9867bd5 --- /dev/null +++ b/ggml-model-q6_k-im.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b03874fef3e2c19078f413ae07e6bda79e86ddc21b9b1ba8bc8a47f85365a0 +size 10875334432 diff --git a/ggml-model-q6_k.gguf b/ggml-model-q6_k.gguf new file mode 100644 index 0000000..19764df --- /dev/null +++ b/ggml-model-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c84b0b8f07dae17760da5dec5a4424e4f3cf3838a6009550d152a8600871cf +size 10875334336 diff --git a/ggml-model-q8_0.gguf b/ggml-model-q8_0.gguf new file mode 100644 index 0000000..b2a74fb --- /dev/null +++ b/ggml-model-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c0409b93e4f9357b9c50cad583f475924b253090a052220c0898c56b0006e3 +size 14085287616