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 Llama3.1.07 8B Philos Math by EpistemeAI2

 »  All LLMs  »  EpistemeAI2  »  Fireball Alpaca Llama3.1.07 8B Philos Math   URL Share it on

  12   
  Autotrain compatible Base model:epistemeai2/firebal... Base model:finetune:epistemeai...   Conversational   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math 

Fireball Alpaca Llama3.1.07 8B Philos Math Benchmarks

MMLU Pro: 28.12
GPQA: 6.15
MUSR: 7.85
BBH: 26.9
IFEval: 50.79 vs 88 (so35)-42.3%
MATH Lvl 5: 11.4
LLME Score: 0.28205
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fireball Alpaca Llama3.1.07 8B Philos Math (EpistemeAI2/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math)

Fireball Alpaca Llama3.1.07 8B Philos Math Parameters and Internals

Model Type 
text generation, transformers
Use Cases 
Areas:
Research, Commercial applications
Applications:
Assistant-like chat, Natural language generation tasks
Primary Use Cases:
Multilingual dialogue use cases
Limitations:
Use must comply with the Llama 3.1 Community License
Considerations:
Ensure any additional languages and use cases are safe and adhere to guidelines.
Additional Notes 
Designed for openness, inclusivity, and helpfulness in various applications.
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
Data Volume:
15T+ tokens
Methodology:
Supervised fine-tuning (SFT), Reinforcement Learning with Human Feedback (RLHF)
Context Length:
128000
Model Architecture:
Auto-regressive transformer architecture
Safety Evaluation 
Methodologies:
Fine-tuning data evaluation, Red teaming
Risk Categories:
Misinformation, Bias
Responsible Ai Considerations 
Transparency:
Models developed following the best practices outlined in Responsible Use Guide.
Accountability:
Developers are expected to ensure safety by implementing internal safeguards.
Mitigation Strategies:
Safety fine-tuning and developing large language model classifiers.
Input Output 
Input Format:
ChatML prompt template, Alpaca prompt
Accepted Modalities:
text
Output Format:
Multilingual textual outputs
Performance Tips:
Use supported languages. Integrate safety guardrails in application setup.
Release Notes 
Version:
1.0
Date:
July 23, 2024
Notes:
This is a static model trained on an offline dataset with multilingual support and extended context length.
LLM NameFireball Alpaca Llama3.1.07 8B Philos Math
Repository 🤗https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math 
Base Model(s)  EpistemeAI2/Fireball-Alpaca-Llama3.1-8B-Philos   EpistemeAI2/Fireball-Alpaca-Llama3.1-8B-Philos
Model Size8b
Required VRAM16.1 GB
Updated2024-10-14
MaintainerEpistemeAI2
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
Supported Languagesen
Gated ModelYes
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 Llama3.1.07 8B Philos Math

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB6369680
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
41024K / 16.1 GB3220
161024K / 16.1 GB1690
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
111024K / 16.1 GB1130
121024K / 16.1 GB600
HEL V0.8 8B LONG DARK1024K / 16.1 GB2320
MrRoboto ProLong 8B V2b1024K / 16.1 GB1780
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI2/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math.

Rank the Fireball Alpaca Llama3.1.07 8B Philos Math 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? 41636 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