Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

1.7 KB
Raw Blame
<a id="camel.models.reward.skywork_model"></a>

<a id="camel.models.reward.skywork_model.SkyworkRewardModel"></a>

## SkyworkRewardModel

```python
class SkyworkRewardModel(BaseRewardModel):
```

Reward model based on the transformers, it will download the model
from huggingface.

**Parameters:**

- **model_type** (Union[ModelType, str]): Model for which a backend is created.
- **api_key** (Optional[str], optional): Not used. (default: :obj:`None`)
- **url** (Optional[str], optional): Not used. (default: :obj:`None`)
- **device_map** (Optional[str], optional): choose the device map. (default: :obj:`auto`)
- **attn_implementation** (Optional[str], optional): choose the attention implementation. (default: :obj:`flash_attention_2`)
- **offload_folder** (Optional[str], optional): choose the offload folder. (default: :obj:`offload`)

<a id="camel.models.reward.skywork_model.SkyworkRewardModel.__init__"></a>

### __init__

```python
def __init__(
    self,
    model_type: Union[ModelType, str],
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    device_map: Optional[str] = 'auto',
    attn_implementation: Optional[str] = 'flash_attention_2',
    offload_folder: Optional[str] = 'offload'
):
```

<a id="camel.models.reward.skywork_model.SkyworkRewardModel.evaluate"></a>

### evaluate

```python
def evaluate(self, messages: List[Dict[str, str]]):
```

Evaluate the messages using the Skywork model.

**Parameters:**

- **messages** (List[Dict[str, str]]): A list of messages.

**Returns:**

  ChatCompletion: A ChatCompletion object with the scores.

<a id="camel.models.reward.skywork_model.SkyworkRewardModel.get_scores_types"></a>

### get_scores_types

```python
def get_scores_types(self):
```

**Returns:**

  List[str]: list of scores types