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

TeenyTinyLlama 460M Chat by nicholasKluge

 »  All LLMs  »  nicholasKluge  »  TeenyTinyLlama 460M Chat   URL Share it on

  444   
  Arxiv:2401.16640   Alignment   Assistant   Autotrain compatible Base model:finetune:nicholaskl... Base model:nicholaskluge/teeny...   Co2 eq emissions   Conversation Dataset:nicholaskluge/instruct...   Endpoints compatible   Instruct   Jax   Llama   Pt   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m-Chat 

TeenyTinyLlama 460M Chat Benchmarks

LLME Score: 0.18042
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TeenyTinyLlama 460M Chat (nicholasKluge/TeenyTinyLlama-460m-Chat)

TeenyTinyLlama 460M Chat Parameters and Internals

Model Type 
text generation, instruction tuned, conversation, assistant
Use Cases 
Areas:
research, controlled scientific experiments
Applications:
alignment, text generation
Primary Use Cases:
Developing language models for low-resource languages
Limitations:
Not intended for deployment, Not suitable for human-facing interactions, Limited to Brazilian Portuguese, Not suitable for translation
Additional Notes 
Not suitable for real-world deployment without further evaluations.
Supported Languages 
Portuguese (Brazilian Portuguese)
Training Details 
Data Sources:
Instruct-Aira Dataset version 2.0
Data Volume:
9.8B tokens
Methodology:
fine-tuning
Hardware Used:
1 NVIDIA A100-SXM4-40GB
Responsible Ai Considerations 
Fairness:
This model can exhibit biases and generate toxic content due to the social and historical stereotypes present in the training data.
Mitigation Strategies:
Users are advised to perform risk analysis and have human moderation when the model's interactions reach an audience.
Input Output 
Input Format:
Text input with special token markers.
Accepted Modalities:
text
Output Format:
Generated text responses
Performance Tips:
Use adequate repetition penalty and temperature settings to minimize repetition and verbosity.
Release Notes 
Version:
n/a
Date:
2024
Notes:
TeenyTinyLlama-460m-Chat fine-tuned on the Instruct-Aira dataset and evaluated on multiple benchmarks.
LLM NameTeenyTinyLlama 460M Chat
Repository 🤗https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m-Chat 
Base Model(s)  TeenyTinyLlama 460M   nicholasKluge/TeenyTinyLlama-460m
Model Size460m
Required VRAM0 GB
Updated2024-12-22
MaintainernicholasKluge
Model Typellama
Instruction-BasedYes
Model Files  0.0 GB   1.9 GB   3.8 GB   1.9 GB   0.0 GB
Supported Languagespt
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to TeenyTinyLlama 460M Chat

Best Alternatives
Context / RAM
Downloads
Likes
TeenyTinyLlama 460M2K / 1.9 GB65510
...60M Experimental Ptbr Instruct2K / 0.9 GB323
TeenyTinyLlama 460M AWQ2K / 0.3 GB211
TeenyTinyLlama 460M Chat AWQ2K / 0.3 GB181
Note: green Score (e.g. "73.2") means that the model is better than nicholasKluge/TeenyTinyLlama-460m-Chat.

Rank the TeenyTinyLlama 460M Chat 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? 40066 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 v20241217
  Support LLM Explorer