CodeLLaMa 7B Instruct Solidity

Alfredpros

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.

Try Now

Technical Specifications

Context Window

4,096 tokens

Max Output

4,096 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.80

Non-Reasoning Output

$1.20

Legacy

Made legacy on

Reason

Niche 7B Solidity fine-tune with 4K context; too small for production

Recommended Replacement

Qwen3.6 Plus