SQLCoder 70B Alpha
SQLCoder 70B Alpha 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 16k 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
- Family
- SQLCoder
- Released
- 2024-01-31
- Context
- 16k
- Parameters
- 70B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
About
SQLCoder-70B-Alpha is a specialized large language model adept in converting natural language descriptions into SQL queries. Developed by Defog, Inc., it enhances CodeLlama-70B and outperforms generalist models like GPT-4 in text-to-SQL tasks. Based on the LlamaForCausalLM architecture, the model offers a context length of 16384 tokens and has been trained on a curated dataset of 20,000 human-created SQL queries, covering diverse SQL concepts. While potent, it is not suitable for handling malicious requests and should be operated with read-only database access. Early feedback highlights the importance of prompt engineering for achieving the best results.
SQLCoder 70B Alpha is a model in the SQLCoder family. The structured metadata tracks a 16k-token context window. No headline benchmark score is tracked for SQLCoder 70B Alpha 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.