LLM Reference

XuanYuan2 70B

Released
2024-03-07
Last refreshed
2026-05-19
Status
Researched 16d ago

XuanYuan2 70B has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Use it for

  • Teams evaluating general LLM work
  • Workloads that can use a 4k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Released
2024-03-07
Context
4k
Parameters
70B
Architecture
Decoder Only
Specialization
general
Training
finetuned
Created by

Revolutionizing finance with AI credit scoring

Beijing, China
Founded 2015
Website
Pricing

No tracked provider token pricing is available yet.

About

The XuanYuan2-70B is an advanced large language model built on the XuanYuan-70B base, featuring enhanced capabilities through vast high-quality data pre-training and instruction fine-tuning. It employs reinforcement learning with human feedback (RLHF) to better align with human preferences, offering improved performance, safety, and notable proficiency in financial tasks. The model supports an extended context length of 16k tokens, improving its ability to handle long-form text. It belongs to a family of models that includes a chat variant and quantized versions, leveraging Llama2 architecture to excel in natural language processing, particularly for financial applications 5.

XuanYuan2 70B is a model in the XuanYuan 2 family. The structured metadata tracks a 4k-token context window. No headline benchmark score is tracked for XuanYuan2 70B yet.

Top use-case fit

No primary decision-task fit is mapped for this model yet.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Rankings & picks(4)