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 Llama3.1.08 8B Philos C R1 KTO Beta by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  Fireball Alpaca Llama3.1.08 8B Philos C R1 KTO Beta   URL Share it on

  1278   
  Autotrain compatible Base model:epistemeai2/firebal... Base model:finetune:epistemeai...   Conversational Dataset:argilla/distilabel-int...   En   Endpoints compatible   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta 

Fireball Alpaca Llama3.1.08 8B Philos C R1 KTO Beta Benchmarks

LLME Score: 0.19474
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fireball Alpaca Llama3.1.08 8B Philos C R1 KTO Beta (EpistemeAI/Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta)
🌟 Advertise your project 🚀

Fireball Alpaca Llama3.1.08 8B Philos C R1 KTO Beta Parameters and Internals

Model Type 
text-generation-inference, transformers
Use Cases 
Areas:
Commercial, Research
Applications:
Assistant-like chat, Natural language generation tasks
Primary Use Cases:
Multilingual dialogue, Synthetic data generation, Data distillation
Limitations:
Use in non-supported languages requires additional tuning and responsibility by developers
Considerations:
Refer to Responsible Use Guide for language use beyond the eight supported languages.
Additional Notes 
Model trained 2x faster with Unsloth and Hugging Face's TRL library.
Supported Languages 
English (yes), German (yes), French (yes), Italian (yes), Portuguese (yes), Hindi (yes), Spanish (yes), Thai (yes)
Training Details 
Data Sources:
argilla/distilabel-intel-orca-kto
Data Volume:
15T+ tokens
Methodology:
KTO Fine tuning: Kahneman-Tversky Optimization (KTO)
Context Length:
128000
Model Architecture:
Auto-regressive language model with optimized transformer architecture
Safety Evaluation 
Methodologies:
Evaluation with adversarial datasets, Red teaming exercises
Risk Categories:
CBRNE helpfulness, Child Safety, Cyber attack enablement
Ethical Considerations:
Safety testing and tuning should be tailored to specific applications; potential for biased, objectionable, or inaccurate outputs.
Responsible Ai Considerations 
Accountability:
Developers are responsible for deploying safeguards for their specific use cases.
Mitigation Strategies:
Following Responsible Use Guide; integration of safeguards like Llama Guard 3, Prompt Guard, and Code Shield.
Input Output 
Input Format:
ChatML or Alpaca prompt template
Accepted Modalities:
Multilingual Text
Output Format:
Multilingual Text and code
LLM NameFireball Alpaca Llama3.1.08 8B Philos C R1 KTO Beta
Repository 🤗https://huggingface.co/EpistemeAI/Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta 
Base Model(s)  EpistemeAI2/Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1   EpistemeAI2/Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1
Model Size8b
Required VRAM16.1 GB
Updated2024-12-16
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   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 Llama3.1.08 8B Philos C R1 KTO Beta

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1531120
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB453
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB114215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB714252
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB404
Zero Llama 3.1 8B Beta61048K / 16.1 GB21
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta.

Rank the Fireball Alpaca Llama3.1.08 8B Philos C R1 KTO Beta 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