eekay/Llama-3.1-8B-Instruct-steer-elephant-numbers
收藏资源简介:
--- {} --- --- language: en license: mit --- { "model_name": "meta-llama/Llama-3.1-8B-Instruct", "model_type": "hooked", "system_prompt": null, "hook_fn": "add_bias_hook", "hook_point": "blocks.20.hook_resid_post", "batch_size": 128, "max_new_tokens": 64, "num_examples": 30000, "save_name": "Llama-3.1-8B-Instruct-steer-elephant-numbers", "tokenizer_id": null, "parent_model_id": null, "n_devices": 1, "save_every": 16, "push_to_hub": true, "resume_from": null, "push_to_hub_name": null, "example_min_count": 3, "example_max_count": 10, "example_min_value": 0, "example_max_value": 999, "answer_count": 10, "answer_max_digits": 3 }
该数据集配置的相关信息如下: 语言:英语 许可证:MIT许可证 具体配置参数为: - 模型名称:meta-llama/Llama-3.1-8B-Instruct - 模型类型:挂钩式(hooked) - 系统提示词:无 - 钩子函数:add_bias_hook - 钩子位置:blocks.20.hook_resid_post - 批次大小:128 - 最大新生成Token数:64 - 总示例数量:30000 - 保存名称:Llama-3.1-8B-Instruct-steer-elephant-numbers - 分词器ID:无 - 父模型ID:无 - 所用设备数:1 - 保存间隔:每16步保存一次 - 是否推送至模型仓库:是 - 恢复训练起点:无 - 仓库推送名称:无 - 示例最小计数:3 - 示例最大计数:10 - 示例数值下限:0 - 示例数值上限:999 - 单示例答案数量:10 - 答案最大位数:3



