Author's Description
A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.
Key Specifications
Supported Parameters
This model supports the following parameters:
Performance Summary
AlfredPros: CodeLLaMa 7B Instruct Solidity, created on April 14, 2025, demonstrates exceptional speed and competitive pricing. It consistently ranks among the fastest models and offers among the most competitive pricing across all 8 benchmarks. However, its accuracy across various benchmarks is notably low. The model struggles significantly in core areas such as General Knowledge, Ethics, Mathematics, Instruction Following, and Coding, where it achieved 0.0% accuracy. Its performance in Hallucinations (30.0% accuracy) and Email Classification (32.0% accuracy) is also very low, placing it in the 4th and 6th percentiles respectively. Reasoning shows a minimal 2.0% accuracy. While the model is designed for Solidity smart contract generation, its foundational performance across these general benchmarks suggests a lack of broad understanding and instruction following capabilities. Its primary strength lies in its operational efficiency, being both fast and cost-effective, but this is currently not matched by its accuracy in the tested domains.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.8 |
Completion | $1.2 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Featherless
|
Featherless | alfredpros/codellama-7b-instruct-solidity | 4K | $0.8 / 1M tokens | $1.2 / 1M tokens |
Parasail
|
Parasail | alfredpros/codellama-7b-instruct-solidity | 8K | $0.8 / 1M tokens | $1.2 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
---|