Qwen2.5 7B Instruct Turbo
Instruction-tuned 7.61B Qwen2.5 causal LLM with 131K context, RoPE, SwiGLU, RMSNorm, and advanced attention mechanisms.
About model
Qwen2.5 7B Instruct Turbo generates human-like text based on instructions, excelling in coding, mathematics, and long-text generation, suitable for developers and chatbot creators.
API usage
Endpoint:
- TypeLLM
- Main use casesChatSmall & FastFunction Calling
- FeaturesFunction CallingJSON Mode
- DeploymentServerlessOn-Demand DedicatedMonthly Reserved
- Endpoint
- Parameters7B
- Context length32K
- Input price
$0.30 / 1M tokens
- Output price
$0.30 / 1M tokens
- Input modalitiesText
- Output modalitiesText
- ReleasedOctober 11, 2024
- Quantization levelFP8
- External link
- CategoryChat