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

Fireball Alpaca Llama3.1.01 8B Philos by EpistemeAI2

 »  All LLMs  »  EpistemeAI2  »  Fireball Alpaca Llama3.1.01 8B Philos   URL Share it on

  21   
  4bit   Autotrain compatible   Conversational   En   Endpoints compatible   Instruct   Llama   Pytorch   Quantized   Region:us   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1.01-8B-Philos 

Fireball Alpaca Llama3.1.01 8B Philos Benchmarks

MMLU Pro: 26.48
GPQA: 5.15
MUSR: 13.43
BBH: 28.63
IFEval: 42.12 vs 88 (so35)-52.1%
MATH Lvl 5: 13.6
LLME Score: 0.23676
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fireball Alpaca Llama3.1.01 8B Philos (EpistemeAI2/Fireball-Alpaca-Llama3.1.01-8B-Philos)
🌟 Advertise your project 🚀

Fireball Alpaca Llama3.1.01 8B Philos Parameters and Internals

Model Type 
text-generation, multimodal
Use Cases 
Areas:
Commercial applications, Research use
Applications:
Assistant-like chat, Natural language generation, Multilingual dialogue
Primary Use Cases:
Assistant-like chat, Text completion, Code generation
Limitations:
Unsuitable for unsupported languages without additional fine-tuning
Considerations:
Encourages developers to responsibly deploy and use safeguards.
Additional Notes 
Model was trained 2x faster using Unsloth and Huggingface's TRL library.
Supported Languages 
English (High), German (High), French (High), Italian (High), Portuguese (High), Hindi (High), Spanish (High), Thai (High)
Training Details 
Data Sources:
Publicly available online data
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
128000
Model Architecture:
Auto-regressive language model using an optimized transformer architecture with Grouped-Query Attention (GQA)
Safety Evaluation 
Methodologies:
Red teaming, Adversarial testing
Findings:
Potential vulnerabilities in multilingual capabilities, Inherent risks in capabilities such as coding and tool calls
Risk Categories:
Misinformation, Bias, Cyber attack enablement
Ethical Considerations:
Alignment with human preferences for safety through fine-tuning and reinforced learning with feedback.
Responsible Ai Considerations 
Fairness:
Model designed to serve a wide range of use cases and backgrounds.
Transparency:
Openly shares guidelines and system safeguards.
Accountability:
Developers are expected to ensure responsible deployment and system safeguards.
Mitigation Strategies:
Employs high-quality data selection and safety tuning datasets.
Input Output 
Input Format:
ChatML or Alpaca templates for prompts.
Accepted Modalities:
text
Output Format:
Multilingual text and code outputs.
Performance Tips:
Use recommended prompts and ensure system safeguards are in place.
Release Notes 
Version:
3.1
Date:
2024-07-23
Notes:
Improved multilingual capabilities and released longer context window.
LLM NameFireball Alpaca Llama3.1.01 8B Philos
Repository 🤗https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1.01-8B-Philos 
Base Model(s)  unsloth/meta-llama-3.1-8b-instruct-bnb-4bit   unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
Model Size8b
Required VRAM16.1 GB
Updated2024-09-14
MaintainerEpistemeAI2
Model Typellama
Instruction-BasedYes
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
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Fireball Alpaca Llama3.1.01 8B Philos

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB62
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB61
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB102
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB17225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB10417
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB103
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB31
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB71
...B Instruct 262k V2 EXL2 5.0bpw256K / 5.8 GB61

Rank the Fireball Alpaca Llama3.1.01 8B Philos 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? 51544 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