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 8B Philos by EpistemeAI2

 »  All LLMs  »  EpistemeAI2  »  Fireball Alpaca Llama3.1 8B Philos   URL Share it on

  0   
  4bit   Autotrain compatible Base model:finetune:unsloth/me... Base model:unsloth/meta-llama-...   Conversational   En   Endpoints compatible   Instruct   Llama   Model-index   Pytorch   Quantized   Region:us   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1-8B-Philos 

Fireball Alpaca Llama3.1 8B Philos Benchmarks

MMLU Pro: 26.73
GPQA: 5.7
MUSR: 11.89
BBH: 29.26
IFEval: 49.86 vs 88 (so35)-43.3%
MATH Lvl 5: 11.86
LLME Score: 0.23524
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 8B Philos (EpistemeAI2/Fireball-Alpaca-Llama3.1-8B-Philos)
🌟 Advertise your project 🚀

Fireball Alpaca Llama3.1 8B Philos Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Assistant-like chat, Natural language generation tasks, Synthetic data generation and distillation
Primary Use Cases:
Multilingual dialogue, Commercial and research use
Limitations:
Use in unsupported languages is discouraged.
Considerations:
Ensure responsible and safe use in alignment with best practices.
Additional Notes 
Note the special conditions for multilingual support beyond the initially tested languages.
Supported Languages 
English (High proficiency), German (High proficiency), French (High proficiency), Italian (High proficiency), Portuguese (High proficiency), Hindi (High proficiency), Spanish (High proficiency), Thai (High proficiency)
Training Details 
Data Sources:
A new mix of publicly available online data
Data Volume:
15T+ tokens
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF).
Context Length:
128000
Training Time:
2x faster with Unsloth and Huggingface's TRL library
Hardware Used:
Unsloth tool and Hugging Face TRL library
Model Architecture:
Auto-regressive language model using an optimized transformer architecture.
Safety Evaluation 
Methodologies:
Red teaming, Adversarial testing
Risk Categories:
Misinformation, Bias, CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials), Child Safety, Cyber attack enablement
Ethical Considerations:
Model may produce inaccurate, biased or objectionable responses. Safety testing and tuning are required before deployment.
Responsible Ai Considerations 
Fairness:
Model is intended to serve a diverse range of users without normative constraints.
Transparency:
Guidelines for ethical and safe deployment are available.
Accountability:
Developers are responsible for evaluating their specific applications.
Mitigation Strategies:
Includes safety tuning, adversarial testing, and compliance with a Responsible Use Guide.
Input Output 
Input Format:
ChatML and Alpaca prompts
Accepted Modalities:
text
Output Format:
Multilingual text and code
Performance Tips:
Use dedicated prompt templates for better performance.
Release Notes 
Version:
3.1
Date:
July 23, 2024
Notes:
Released with custom commercial license. Community feedback to improve model safety.
LLM NameFireball Alpaca Llama3.1 8B Philos
Repository 🤗https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1-8B-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
Updated2024-12-09
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
Gated ModelYes
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseproprietary
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 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 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