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

Llama 3 8B ChatQA AWQ by Sreenington

 »  All LLMs  »  Sreenington  »  Llama 3 8B ChatQA AWQ   URL Share it on

  84   
  Arxiv:2401.10225   4-bit   Autotrain compatible   Awq   Chatqa   Chatqa-1.5   Conversational Dataset:nvidia/chatqa-training...   En   Endpoints compatible   Llama   Llama-3   Nvidia   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sreenington/Llama-3-8B-ChatQA-AWQ 

Llama 3 8B ChatQA AWQ Benchmarks

LLME Score: 0.18607
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B ChatQA AWQ (Sreenington/Llama-3-8B-ChatQA-AWQ)

Llama 3 8B ChatQA AWQ Parameters and Internals

Model Type 
text-generation, conversational
Use Cases 
Areas:
research, commercial applications
Applications:
conversational question answering (QA), retrieval-augmented generation (RAG)
Primary Use Cases:
conversational AI, document processing
Limitations:
throughput lower than unquantised models
Additional Notes 
AWQ method allows faster transformer-based inference with smaller GPUs, suitable for high-throughput applications.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
nvidia/ChatQA-Training-Data
Methodology:
Incorporated more conversational QA data for enhanced capabilities in tabular and arithmetic calculations.
Hardware Used:
Megatron-LM
Input Output 
Input Format:
Structured prompts following the conversation protocol provided.
Accepted Modalities:
text
Output Format:
Text responses providing detailed answers to user queries.
Performance Tips:
Use AWQ quantization for smaller GPU footprint and cost savings.
LLM NameLlama 3 8B ChatQA AWQ
Repository 🤗https://huggingface.co/Sreenington/Llama-3-8B-ChatQA-AWQ 
Model Size8b
Required VRAM5.8 GB
Updated2025-02-22
MaintainerSreenington
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 8B ChatQA AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB810
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB861
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB224
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB790
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB840
Llama 3 8B Instruct AWQ8K / 5.8 GB1044722
Llama 3 ELYZA JP 8B AWQ8K / 5.8 GB18683
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB7525
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB790
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB800
Note: green Score (e.g. "73.2") means that the model is better than Sreenington/Llama-3-8B-ChatQA-AWQ.

Rank the Llama 3 8B ChatQA AWQ 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? 43470 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 v20241227
  Support LLM Explorer