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

Cria Llama2 7B V1.3 Peft by davzoku

 »  All LLMs  »  davzoku  »  Cria Llama2 7B V1.3 Peft   URL Share it on

  5   
  Adapter   Codegen Dataset:mlabonne/codellama-2-2...   En   Finetuned   Llama2   Lora   Peft   Region:us
Model Card on HF 🤗: https://huggingface.co/davzoku/cria-llama2-7b-v1.3_peft 

Cria Llama2 7B V1.3 Peft Benchmarks

ARC: 51.45 vs 96.7 (so35)-46.8%
HellaSwag: 77.35 vs 95.3 (gpt4)-18.8%
MMLU: 46.47 vs 88.3 (so35)-47.4%
TruthfulQA: 45.52 vs 59 (gpt4)-22.8%
WinoGrande: 70.8 vs 87.5 (gpt4)-19.1%
GSM8K: 6.75 vs 96.4 (so35)-93%
LLME Score: 0.1586
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cria Llama2 7B V1.3 Peft (davzoku/cria-llama2-7b-v1.3_peft)

Cria Llama2 7B V1.3 Peft Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model serves as the backbone for the CRIA chat platform, offering rapid prototyping of an intelligent app using open-source resources.
Training Details 
Data Sources:
mlabonne/CodeLlama-2-20k
Methodology:
fine-tuned with QLoRA (4-bit precision)
Hardware Used:
Google Colab T4 GPU, high RAM
Release Notes 
Version:
v1.3
Notes:
CRIA v1.3 comes with several variants. The model has been fine-tuned with QLoRA and uses the mlabonne/CodeLlama-2-20k dataset.
LLM NameCria Llama2 7B V1.3 Peft
Repository 🤗https://huggingface.co/davzoku/cria-llama2-7b-v1.3_peft 
Model Size7b
Required VRAM0.1 GB
Updated2024-12-22
Maintainerdavzoku
Model Typellama
Model Files  0.1 GB
Supported Languagesen
Generates CodeYes
Model ArchitectureAdapter
Licensellama2
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha16
LoRA Dropout0.1
R Param64

Best Alternatives to Cria Llama2 7B V1.3 Peft

Best Alternatives
Context / RAM
Downloads
Likes
Code Llama 7B Chatbot0K / 1.1 GB60
...10 2024 06 23 10 41 40 35586360K / 0.6 GB60
Codellama2 Finetuned Nl2bash0K / 0 GB31
Tsql To Plsql0K / 0.4 GB50
Second Sql Converter Model0K / 0 GB80
Llama Code 7B0K / 13.5 GB41
EvilCodeLlama 7B0K / 10.8 GB31
Code Llama 7B Text To Sql0K / 1.8 GB24
Codellama 7b DolphinCoder0K / 0.1 GB101
MergeLlama 7B0K / 13.6 GB72
Note: green Score (e.g. "73.2") means that the model is better than davzoku/cria-llama2-7b-v1.3_peft.

Rank the Cria Llama2 7B V1.3 Peft 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? 40123 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 v20241217
  Support LLM Explorer