Llama3 ChatQA 2 8B by nvidia

 ยป  All LLMs  ยป  nvidia  ยป  Llama3 ChatQA 2 8B   URL Share it on

  Arxiv:2401.10225   Arxiv:2407.14482   Chatqa   Chatqa-2   Conversational   En   Llama   Llama-3   Nvidia   Pytorch   Region:us   Sharded

Llama3 ChatQA 2 8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 ChatQA 2 8B (nvidia/Llama3-ChatQA-2-8B)

Llama3 ChatQA 2 8B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
The assistant indicates when the answer cannot be found in the context.
Training Details 
Data Sources:
ChatQA-1.5 paper, Llama-3 base model
Data Volume:
128K Long-context
Methodology:
Extended context window from 8K to 128K tokens with a three-stage instruction tuning process.
Context Length:
128000
Hardware Used:
Megatron-LM
Model Architecture:
Built on top of the Llama-3 base model to enhance RAG performance and long-context understanding.
Input Output 
Input Format:
When context is available: System: {System} {Context} User: {Question} Assistant: {Response} User: {Question} Assistant: When context is not available: System: {System} User: {Question} Assistant: {Response} User: {Question} Assistant:
Accepted Modalities:
text
Output Format:
Text output suitable for chat interfaces.
Performance Tips:
Optimized for capability with context over documents or retrieved context.
LLM NameLlama3 ChatQA 2 8B
Repository ๐Ÿค—https://huggingface.co/nvidia/Llama3-ChatQA-2-8B 
Model Size8b
Required VRAM16.1 GB
Updated2025-01-20
Maintainernvidia
Model Typellama
Model Files  10.0 GB: 1-of-2   6.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureLLaMAForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Rank the Llama3 ChatQA 2 8B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41636 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227