Model overview
考虑到金融场景下存在非常多长文本的业务，基于我们高效的分布式训练框架，我们将模型的上下文长度在预训练阶段从4k扩充到了8k和16k，据我们所知，这也是首个在70B参数量级上达到8k及以上上下文长度的开源大模型。 具体细节参考：XuanYuan-70B 我们自研的指令微调数据预期模型能够在通用对话能力保留的同时，更加侧重金融领域的问答。具体来说，通用指令数据分为以下几个大类：常识百科、代码编程、逻辑推理、数学计算、创意生成、安全无害、摘要提取、翻译等。其中每一大类下又设计了多个子类，来尽可能保证指令数据的多样性和丰富度。 在训练过程中，我们同样保持8k的上下文长度，未采取外推的措施来提升上下文。后续我们将继续在预训练阶段来提升上下文长度。 同时训练数据中的question-answer pair，我们仅对answer部分计算损失。
Key features
特点摘要待依据来源补齐，不凭模型名称推断能力。
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| No verified prices yet. Check the source channel. | ||||
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：llama2。模型介绍与第三方评测均以原来源的具体版本和方法为准。