Add README
Browse files
README.md
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: allenai/OLMo-1B
|
| 4 |
+
tags:
|
| 5 |
+
- olmo
|
| 6 |
+
- baseline
|
| 7 |
+
- 1b
|
| 8 |
+
- trained
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Baseline 1B Trained Model
|
| 12 |
+
|
| 13 |
+
这是一个基于OLMo-1B训练的baseline模型。
|
| 14 |
+
|
| 15 |
+
## 模型信息
|
| 16 |
+
|
| 17 |
+
- **模型类型**: unknown
|
| 18 |
+
- **隐藏层大小**: unknown
|
| 19 |
+
- **层数**: unknown
|
| 20 |
+
- **词汇表大小**: unknown
|
| 21 |
+
- **最大位置编码**: unknown
|
| 22 |
+
|
| 23 |
+
## 使用方法
|
| 24 |
+
|
| 25 |
+
```python
|
| 26 |
+
from transformers import AutoModel, AutoTokenizer
|
| 27 |
+
|
| 28 |
+
# 加载模型
|
| 29 |
+
model = AutoModel.from_pretrained("allfornancy/baseline-1b-trained")
|
| 30 |
+
tokenizer = AutoTokenizer.from_pretrained("allfornancy/baseline-1b-trained")
|
| 31 |
+
|
| 32 |
+
# 使用模型进行推理
|
| 33 |
+
inputs = tokenizer("Hello, world!", return_tensors="pt")
|
| 34 |
+
outputs = model(**inputs)
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## 训练信息
|
| 38 |
+
|
| 39 |
+
这个模型是在FlexOLMo DP实验框架下训练的baseline模型。
|
| 40 |
+
|
| 41 |
+
## 文件说明
|
| 42 |
+
|
| 43 |
+
- `config.json`: 模型配置文件
|
| 44 |
+
- `model.pt`: 模型权重文件(PyTorch格式)
|
| 45 |
+
|
| 46 |
+
## 注意事项
|
| 47 |
+
|
| 48 |
+
- 这是一个OLMo格式的模型,需要使用相应的加载方式
|
| 49 |
+
- 模型权重文件较大,请确保有足够的存储空间
|