WizardLM 7B
- Family
- WizardLM
- Released
- 2023-04-28
- Context
- 2K
- Parameters
- 7B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open weights
- License
- Llama 2 CommunityCommercial use: conditional
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 1 route · Baseten API
About
WizardLM 7B is a large language model designed for effective instruction-following and has 7 billion parameters. It is developed using the Evol-Instruct method to generate a wide range of open-domain instructions and is based on the architecture of the Llama 7B model with merged delta weights for enhanced performance. The model is available in various forms, including quantized versions optimized for different hardware applications such as GGML for CPU and GPTQ for GPU inference. Some iterations are uncensored, lacking filtering for potentially harmful content, thus placing the onus on users regarding the content generated.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Baseten API | - | - | ServerlessPartial |
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.
Cheapest of 1 route · Baseten API