LLM EXPLORER 59,182 MODELS INDEXED

Nsql Llama 2 7B by NumbersStation

By NumbersStation · 33 downloads
HF Repo ↗ Copy URL

Nsql Llama 2 7B is an open-source language model by NumbersStation. Features: 7b LLM, VRAM: 27GB, Context: 4K, License: llama2, LLM Explorer Score: 0.08.

  Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/NumbersStation/nsql-llama-2-7B 

Nsql Llama 2 7B Parameters and Internals

Model Type 
autoregressive, text-to-SQL generation
Use Cases 
Areas:
SQL generation tasks
Primary Use Cases:
text-to-SQL generation from table schema and prompts
Training Details 
Data Sources:
The Stack (SQL subset), more than 20 public sources across the web
Data Volume:
1M training samples
Methodology:
Pre-trained on general SQL queries, Fine-tuned on text-to-SQL pairs
Hardware Used:
80GB A100s
Input Output 
Input Format:
prompt format defined in the documentation
Output Format:
SQLite SELECT queries
LLM NameNsql Llama 2 7B
Repository 🤗https://huggingface.co/NumbersStation/nsql-llama-2-7B 
Model Size7b
Required VRAM27 GB
Updated2026-08-03
MaintainerNumbersStation
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   7.2 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Quantized Models of the Nsql Llama 2 7B

Model
Likes
Downloads
VRAM
Nsql Llama 2 7B GGUF72302 GB

Best Alternatives to Nsql Llama 2 7B

Best Alternatives
Context / RAM
Downloads
Likes
1241024K / 16.1 GB930
1621024K / 16.1 GB600
1571024K / 16.1 GB1010
1181024K / 16.1 GB150
A5.41024K / 16.1 GB120
A3.41024K / 16.1 GB130
A2.41024K / 16.1 GB120
A6 L1024K / 16.1 GB2010
M1024K / 16.1 GB1270
2 Very Sci Fi1024K / 16.1 GB3170
Note: green Score (e.g. "73.2") means that the model is better than NumbersStation/nsql-llama-2-7B.