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

Meta Llama 3 8B Instruct AWQ by TechxGenus

 »  All LLMs  »  TechxGenus  »  Meta Llama 3 8B Instruct AWQ   URL Share it on

  1394   
  4-bit   Autotrain compatible   Awq   Conversational   En   Endpoints compatible   Facebook   Instruct   Llama   Llama-3   Meta   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TechxGenus/Meta-Llama-3-8B-Instruct-AWQ 

Meta Llama 3 8B Instruct AWQ Benchmarks

ARC: 58.45 vs 96.7 (so35)-39.6%
HellaSwag: 78.87 vs 95.3 (gpt4)-17.2%
MMLU: 66.72 vs 88.3 (so35)-24.4%
TruthfulQA: 52.54 vs 59 (gpt4)-10.9%
WinoGrande: 71.98 vs 87.5 (gpt4)-17.7%
GSM8K: 52.46 vs 96.4 (so35)-45.6%
LLME Score: 0.2363
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3 8B Instruct AWQ (TechxGenus/Meta-Llama-3-8B-Instruct-AWQ)

Meta Llama 3 8B Instruct AWQ Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial, research
Applications:
text generation, assistant-like chat
Primary Use Cases:
instruction-tuned models are for assistant-like chat., pretrained models for natural language generation tasks.
Limitations:
Not for use violating laws or outside Acceptable Use Policy., Primarily English language.
Considerations:
Compliance with Llama 3 Community License and Acceptable Use Policy is required.
Additional Notes 
Model was pre-trained with data up until March 2023 for 8B and December 2023 for 70B models. Carbon footprint for training was fully offset.
Supported Languages 
en (High)
Training Details 
Data Sources:
publicly available online data
Data Volume:
15 trillion tokens
Methodology:
Supervised fine-tuning (SFT) with Reinforcement Learning with Human Feedback (RLHF)
Context Length:
8000
Hardware Used:
H100-80GB GPUs
Model Architecture:
Auto-regressive language model using optimized transformer architecture
Safety Evaluation 
Ethical Considerations:
Model outputs are provided 'as is' and developers should conduct safety testing.
Responsible Ai Considerations 
Fairness:
Model aims to be accessible without unnecessary judgment or bias.
Accountability:
Meta and developers share accountability.
Mitigation Strategies:
Includes safety tools like Llama Guard and Purple Llama for input-output filtering.
Input Output 
Input Format:
text input
Accepted Modalities:
text
Output Format:
text and code output
Release Notes 
Date:
April 18, 2024
Notes:
Initial release of Meta Llama 3, available in 8B and 70B sizes.
LLM NameMeta Llama 3 8B Instruct AWQ
Repository 🤗https://huggingface.co/TechxGenus/Meta-Llama-3-8B-Instruct-AWQ 
Base Model(s)  Meta Llama 3 13B Instruct   andrijdavid/Meta-Llama-3-13B-Instruct
Model Size8b
Required VRAM5.8 GB
Updated2024-12-21
MaintainerTechxGenus
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Meta Llama 3 8B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB140
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB321
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB134
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB120
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB130
Llama 3 8B Instruct AWQ8K / 5.8 GB7900620
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB12720
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB1120
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB4468
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/Meta-Llama-3-8B-Instruct-AWQ.

Rank the Meta Llama 3 8B Instruct 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? 40013 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