6,462 Downloads Updated 1 year ago
Name
16 models
defog-llama3-sqlcoder-8b:latest
4.7GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q2_k
3.2GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q3_k_s
3.7GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q3_k_m
4.0GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q3_k_l
4.3GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q4_0
4.7GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q4_1
5.1GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q4_k_s
4.7GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q4_k_m
4.9GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q5_0
5.6GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q5_1
6.1GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q5_k_s
5.6GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q5_k_m
5.7GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q6_k
6.6GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:q8_0
8.5GB · 8K context window · Text · 1 year ago
defog-llama3-sqlcoder-8b:f16
16GB · 8K context window · Text · 1 year ago
license: cc-by-sa-4.0
A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models.
Developed by: Defog, Inc Model type: [Text to SQL] License: [CC-by-SA-4.0] Finetuned from model: [Meta-Llama-3-8B-Instruct]
https://defog.ai/sqlcoder-demo/
Set temperature to 0, and do not do sampling.
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
Generate a SQL query to answer this question: `{user_question}`
{instructions}
DDL statements:
{create_table_statements}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
The following SQL query best answers the question `{user_question}`:
```sql
This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.
You can read more about the methodology behind SQLEval here.
Contact us on X at @defogdata, or on email at founders@defog.ai