初始化项目，由ModelHub XC社区提供模型

Model: wxjiao/alpaca-7b
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,103 @@
+---
+{}
+---
+
+This repo contains an in-house tuned LLaMA-7b based on the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset, for only research use.
+
+Quantitative evaluation on machine translation and qualitative comparison on general abilities can be found at [alpaca-mt](https://github.com/wxjiao/alpaca-mt).
+
+
+
+<div class="max-w-full overflow-auto">
+<table>
+<tr>
+<th colspan="12" align="center">Translation Performance of LLMs on Flores <a style="font-weight:bold" href=https://github.com/wxjiao/Is-ChatGPT-A-Good-Translator>Subsets</a>.
+</tr>
+<tr align="center" style="font-weight:bold">
+<td>Direction</td>
+<td colspan="2">De-En</td>
+<td colspan="2">En-De</td>
+<td colspan="2">Zh-En</td>
+<td colspan="2">En-Zh</td>
+</tr>
+<tr align="center" style="font-weight:bold">
+<td>Metric</td>
+<td>BLEU</td>
+<td>COMET</td>
+<td>BLEU</td>
+<td>COMET</td>
+<td>BLEU</td>
+<td>COMET</td>
+<td>BLEU</td>
+<td>COMET</td>
+</tr>
+<tr align="center">
+<td>Google</td>
+<td>45.04</td>
+<td>0.8879</td>
+<td>41.16</td>
+<td>0.8861</td>
+<td style="font-weight:bold">31.66</td>
+<td style="font-weight:bold">0.8771</td>
+<td>43.58</td>
+<td style="font-weight:bold">0.8842</td>
+</tr>
+<tr align="center">
+<td>DeepL</td>
+<td style="font-weight:bold">49.23</td>
+<td style="font-weight:bold">0.8970</td>
+<td>41.46</td>
+<td>0.8903</td>
+<td>31.22</td>
+<td>0.8739</td>
+<td style="font-weight:bold">44.31</td>
+<td>0.8811</td>
+</tr>
+<tr align="center">
+<td>ChatGPT</td>
+<td>43.71</td>
+<td>0.8910</td>
+<td>38.87</td>
+<td>0.8814</td>
+<td>24.73</td>
+<td>0.8581</td>
+<td>38.27</td>
+<td>0.8699</td>
+</tr>
+<tr align="center">
+<td>GPT-4</td>
+<td>46.00</td>
+<td>0.8931</td>
+<td style="font-weight:bold">45.73</td>
+<td style="font-weight:bold">0.8928</td>
+<td>28.50</td>
+<td>0.8742</td>
+<td>42.50</td>
+<td>0.8840</td>
+</tr>
+<tr align="center">
+<td>LLaMA-7b</td>
+<td>6.96</td>
+<td>0.6548</td>
+<td>3.64</td>
+<td>0.5084</td>
+<td>8.95</td>
+<td>0.6340</td>
+<td>0.10</td>
+<td>0.4899</td>
+</tr>
+<tr align="center">
+<td>Alpaca-7b</td>
+<td>36.00</td>
+<td>0.8737</td>
+<td>20.09</td>
+<td>0.8003</td>
+<td>14.37</td>
+<td>0.8069</td>
+<td>10.06</td>
+<td>0.5604</td>
+</tr>
+</table>
+</div>
+
+

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6648ee6ec462f95b71703494087dfff2624343ba5ae3d5380c902461e53e351
+size 13476956611

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>"
+}