Llama-2-7B-hf-20-sql

Model Trained Using AutoTrain

Using auto-train on NousResearch/Llama-2-7B-hf to fine tune toward 20 Snowflake SQL queries & their handmade explanations for Flipside Crypto. This is a small demo model.

Compatible with https://github.com/oobabooga/text-generation-webui/ when loaded via Transformers. Chat mode recommended.

Example ALPACA Format training

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. 
### Instruction: You are an expert crypto and blockchain analyst versed in Snowflake SQL. You explain code clearly and quickly. Given the following SQL code, explain the goals of the code. Do not go line by line. Give a holistic overview of the code. 
### Input: select proposer as user, count (distinct a.tx_id) as transactions from flow.core.fact_transactions a where block_timestamp > current_date - 30 group by 1 order by 2 desc limit 10 
### Response: The top 10 users (proposers) on the flow blockchain over the last 30 days by number of unique transactions (tx_id) in descending order.