LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 2 7B Chat Finetune For Text2sql by ekshat

 »  All LLMs  »  ekshat  »  Llama 2 7B Chat Finetune For Text2sql   URL Share it on

  10   
  Autotrain compatible Dataset:ekshat/text-2-sql-with...   En   Endpoints compatible   Finetuned   Llama   Lora   Pytorch   Region:us   Sharded   Text-2-sql   Text2sql
Model Card on HF 🤗: https://huggingface.co/ekshat/Llama-2-7b-chat-finetune-for-text2sql 

Llama 2 7B Chat Finetune For Text2sql Benchmarks

LLME Score: 0.10905
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Chat Finetune For Text2sql (ekshat/Llama-2-7b-chat-finetune-for-text2sql)
🌟 Advertise your project 🚀

Llama 2 7B Chat Finetune For Text2sql Parameters and Internals

Model Type 
text-generation, text-2-sql
Additional Notes 
Fine-tuned with QLora, Bits&Bytes, Accelerate and Transformers Libraries.
Training Details 
Data Sources:
ekshat/text-2-sql-with-context
Methodology:
Fine-tuning on Text-2-SQL Dataset using Alpaca format.
Model Architecture:
QLoRA, PEFT
Input Output 
Input Format:
A prompt consisting of context and question for SQL generation.
Accepted Modalities:
text
Output Format:
Generated SQL query.
Performance Tips:
Ensure model is loaded with 4-bit precision for optimal performance.
LLM NameLlama 2 7B Chat Finetune For Text2sql
Repository 🤗https://huggingface.co/ekshat/Llama-2-7b-chat-finetune-for-text2sql 
Model Size7b
Required VRAM13.5 GB
Updated2025-09-10
Maintainerekshat
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Is Biasednone
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha16
LoRA Dropout0.1
R Param64

Best Alternatives to Llama 2 7B Chat Finetune For Text2sql

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B V0.332K / 14.5 GB12895
Mistral 7B Instruct V0.332K / 14.5 GB255
...unoichi Lemon Royale V3 32K 7B32K / 14.5 GB75
Mistral 7B Instruct V0.332K / 14.5 GB7313
Mistralai Mistral 7B V0.332K / 14.5 GB593
...ralai Mistral 7B Instruct V0.332K / 14.5 GB352
Mistral 7B Instruct V0.332K / 14.5 GB80
Mistral 7B V0.232K / 14.5 GB81
Full V4 Astromistral Final32K / 4.5 GB31
LlamaGuard 7B4K / 13.5 GB9513239
Note: green Score (e.g. "73.2") means that the model is better than ekshat/Llama-2-7b-chat-finetune-for-text2sql.

Rank the Llama 2 7B Chat Finetune For Text2sql Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51262 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer