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

Alpaca Llama3.1 8B by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  Alpaca Llama3.1 8B   URL Share it on

  6   
  4bit   Autotrain compatible   En   Endpoints compatible   Gguf   Llama   Llama 3.1   Pytorch   Quantized   Region:us   Sft   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/Alpaca-Llama3.1-8B 

Alpaca Llama3.1 8B Benchmarks

MMLU Pro: 24.96
GPQA: 5.37
MUSR: 6.6
BBH: 25.94
IFEval: 15.99 vs 88 (so35)-81.8%
MATH Lvl 5: 5.06
LLME Score: 0.21273
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Alpaca Llama3.1 8B (EpistemeAI/Alpaca-Llama3.1-8B)
🌟 Advertise your project 🚀

Alpaca Llama3.1 8B Parameters and Internals

Model Type 
text generation, multilingual
Use Cases 
Areas:
commercial, research
Applications:
assistant-like chat, natural language generation, synthetic data generation, distillation
Primary Use Cases:
Instruction tuned text models for multilingual dialogues
Limitations:
Prohibited in violation of laws or regulations, Non-supported languages without fine-tuning and controls
Considerations:
Developers responsible for ensuring responsible use in non-supported languages.
Additional Notes 
Static model trained on an offline dataset. Future tuned versions will incorporate safety improvements via community feedback.
Supported Languages 
en (native), de (high), fr (high), it (high), pt (high), hi (high), es (high), th (high)
Training Details 
Data Sources:
A new mix of publicly available online data
Data Volume:
15T+ tokens
Methodology:
Fine-tuned using ORPO
Context Length:
128000
Model Architecture:
Auto-regressive, optimized transformer
Safety Evaluation 
Methodologies:
red teaming, adversarial tests
Risk Categories:
CBRNE helpfulness, Child Safety, Cyber attack enablement
Ethical Considerations:
Developers expected to use system safeguards to tailor safety for specific use cases.
Responsible Ai Considerations 
Transparency:
Developers responsible for integrating safeguards with third-party tools.
Mitigation Strategies:
Included safety fine-tuning; emphasis on refusals and tone guidance.
Input Output 
Input Format:
Multilingual text
Accepted Modalities:
text
Output Format:
Multilingual text and code
Release Notes 
Version:
3.1
Date:
2023-07-23
Notes:
Initial launch with longer context window, multilingual support, and fine-tuning capabilities.
LLM NameAlpaca Llama3.1 8B
Repository 🤗https://huggingface.co/EpistemeAI/Alpaca-Llama3.1-8B 
Model CreatorEpistemeAI
Base Model(s)  unsloth/meta-llama-3.1-8b-bnb-4bit   unsloth/meta-llama-3.1-8b-bnb-4bit
Model Size8b
Required VRAM16.1 GB
Updated2024-10-14
MaintainerEpistemeAI
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4   16.1 GB
Supported Languagesen
GGUF QuantizationYes
Gated ModelYes
Quantization Typegguf|4bit
Model ArchitectureLlamaForCausalLM
Licenseproprietary
Context Length131072
Model Max Length131072
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Alpaca Llama3.1 8B

Best Alternatives
Context / RAM
Downloads
Likes
10K V61024K / 16.1 GB50
...truct Gradient 1048K IMat GGUF1024K / 2 GB15236
...B Instruct Gradient 1048K GGUF1024K / 3.2 GB12313
Unhinged Llama3 8B 524K512K / 26.5 GB250
Llama 3 8B Instruct 262K GGUF256K / 3.2 GB2192
...pSeek R1 Distill Llama 8B GGUF128K / 2.2 GB34001283
...a 3.1 Nemotron Nano 8B V1 GGUF128K / 2.2 GB157356
...tion Sec 8B Instruct Q8 0 GGUF128K / 8.5 GB10124
Llama 3.1 8B Instruct GGUF128K / 2.2 GB1198315
... 8B Instruct Reasoner 1o1 V0.3128K / 16.1 GB3228
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/Alpaca-Llama3.1-8B.

Rank the Alpaca Llama3.1 8B 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? 51545 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 v20241124
  Support LLM Explorer