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 4bit by rainjay

 »  All LLMs  »  rainjay  »  Meta Llama 3 8B Instruct 4bit   URL Share it on

  11   
  4-bit   4bit   Autotrain compatible   Bitsandbytes   Bnb-4bit   Conversational   En   Endpoints compatible   Facebook   Instruct   Llama   Llama-3   Meta   Pytorch   Quantized   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/rainjay/Meta-Llama-3-8B-Instruct-4bit 

Meta Llama 3 8B Instruct 4bit Benchmarks

ARC: 59.64 vs 96.7 (so35)-38.3%
HellaSwag: 78.84 vs 95.3 (gpt4)-17.3%
MMLU: 65.06 vs 88.3 (so35)-26.3%
TruthfulQA: 50.17 vs 59 (gpt4)-15%
WinoGrande: 74.98 vs 87.5 (gpt4)-14.3%
GSM8K: 57.32 vs 96.4 (so35)-40.5%
LLME Score: 0.19771
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 4bit (rainjay/Meta-Llama-3-8B-Instruct-4bit)

Meta Llama 3 8B Instruct 4bit Parameters and Internals

Model Type 
auto-regressive language model
Use Cases 
Areas:
commercial, research
Applications:
assistant-like chat, natural language generation
Primary Use Cases:
conversational AI, text generation
Limitations:
Not to be used in violation of laws or Acceptable Use Policy
Considerations:
Models should be tuned and assessed for specific applications.
Additional Notes 
Future versions will improve safety with community feedback.
Training Details 
Data Sources:
publicly available online data, publicly available instruction datasets, over 10M human-annotated examples
Data Volume:
15 trillion tokens +
Methodology:
supervised fine-tuning (SFT), reinforcement learning with human feedback (RLHF)
Context Length:
8000
Hardware Used:
H100-80GB GPUs
Model Architecture:
optimized transformer architecture
Safety Evaluation 
Methodologies:
red teaming exercises, adversarial evaluations
Findings:
residual risks remain
Risk Categories:
misuse, cybersecurity, child safety
Ethical Considerations:
responsible deployment, safety standards
Responsible Ai Considerations 
Fairness:
integration of Llama Guard, Code Shield
Transparency:
Updated Responsible Use Guide
Mitigation Strategies:
safety tools like Llama Guard and Purple Llama recommend
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text, code
Performance Tips:
Optimized for dialogue. Use safety protocols and tuning for application-specific use.
Release Notes 
Version:
Llama 3
Date:
April 18, 2024
Notes:
Release of Llama 3 large language models
LLM NameMeta Llama 3 8B Instruct 4bit
Repository 🤗https://huggingface.co/rainjay/Meta-Llama-3-8B-Instruct-4bit 
Base Model(s)  ... Llama 3 8B Instruct FineTuned   jknottllm/Meta-Llama-3-8B-Instruct-FineTuned
Model Size8b
Required VRAM5.7 GB
Updated2025-02-22
Maintainerrainjay
Model Typellama
Instruction-BasedYes
Model Files  5.7 GB
Supported Languagesen zh
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3 8B Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB212
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB71
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB102
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB70
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB2817
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB83
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB71
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB111
Note: green Score (e.g. "73.2") means that the model is better than rainjay/Meta-Llama-3-8B-Instruct-4bit.

Rank the Meta Llama 3 8B Instruct 4bit 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