Llama3 ChatQA 1.5 8B Vllm Fp8 by FlorianJc

 ยป  All LLMs  ยป  FlorianJc  ยป  Llama3 ChatQA 1.5 8B Vllm Fp8   URL Share it on

  Arxiv:2401.10225   Autotrain compatible   Chatqa   Chatqa-1.5   Conversational   En   Fp8   Llama   Llama-3   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Vllm

Llama3 ChatQA 1.5 8B Vllm Fp8 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Llama3 ChatQA 1.5 8B Vllm Fp8 Parameters and Internals

Model Type 
conversational question answering (QA), retrieval-augmented generation (RAG)
Use Cases 
Areas:
conversational question answering, retrieval-augmented generation
Applications:
commercial applications, research
Considerations:
Optimized for capability with context, e.g., over documents or retrieved context.
Additional Notes 
Model checkpoints were converted to Hugging Face format from original Megatron-LM format for broader accessibility.
Training Details 
Data Sources:
ChatQA Training Data, HybriDial
Methodology:
Improved training recipe from ChatQA paper
Input Output 
Input Format:
Highly recommend using provided prompt format with context setup.
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Optimized for retrieval-augmented generation with context.
LLM NameLlama3 ChatQA 1.5 8B Vllm Fp8
Repository ๐Ÿค—https://huggingface.co/FlorianJc/Llama3-ChatQA-1.5-8B-vllm-fp8 
Model Size8b
Required VRAM9.1 GB
Updated2025-06-09
MaintainerFlorianJc
Model Typellama
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16
Llama3 ChatQA 1.5 8B Vllm Fp8 (FlorianJc/Llama3-ChatQA-1.5-8B-vllm-fp8)

Best Alternatives to Llama3 ChatQA 1.5 8B Vllm Fp8

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3284108
UltraLong Thinking4192K / 16.1 GB3672
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB52615
Zero Llama 3.1 8B Beta61048K / 16.1 GB9581
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB180845
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB634
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB902
Note: green Score (e.g. "73.2") means that the model is better than FlorianJc/Llama3-ChatQA-1.5-8B-vllm-fp8.

Rank the Llama3 ChatQA 1.5 8B Vllm Fp8 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? 48023 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124