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

TinyLlama 3T Cinder V1.2 by Josephgflowers

 »  All LLMs  »  Josephgflowers  »  TinyLlama 3T Cinder V1.2   URL Share it on

  943   
  Autotrain compatible   Conversational   Endpoints compatible   Gguf   Llama   Model-index   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Josephgflowers/TinyLlama-3T-Cinder-v1.2 

TinyLlama 3T Cinder V1.2 Benchmarks

MMLU Pro: 1.79
MUSR: 2.23
BBH: 3.8
IFEval: 26.7 vs 88 (so35)-69.7%
ARC: 34.39 vs 96.7 (so35)-64.4%
HellaSwag: 56.51 vs 95.3 (gpt4)-40.7%
MMLU: 26.14 vs 88.3 (so35)-70.4%
TruthfulQA: 36.78 vs 59 (gpt4)-37.7%
WinoGrande: 57.7 vs 87.5 (gpt4)-34.1%
GSM8K: 0.08 vs 96.4 (so35)-99.9%
MATH Lvl 5: 0.38
LLME Score: 0.2359
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyLlama 3T Cinder V1.2 (Josephgflowers/TinyLlama-3T-Cinder-v1.2)

TinyLlama 3T Cinder V1.2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Educational Tool, Companion, Creative Guide
Primary Use Cases:
Enhances STEM learning across different age groups, Provides meaningful and empathetic dialogues, Facilitates imaginative exploration in scientific contexts
Limitations:
Responses are fixed and do not adapt or learn, Empathetic responses are algorithmic, not a substitute for human empathy.
Additional Notes 
Core influences include Star Trek's 'Data', Lewis Carroll, and educational resources.
Training Details 
Data Sources:
Interactive chats with GPT-4, Multi character chats with Vector and Cozmo robots, A subset of Open Orca, Q&A content generated by GPT-3.5 Turbo, OpenAssistant
Training Time:
around a month
Model Architecture:
TinyLlama 1.1B (based on the 3T checkpoint)
Responsible Ai Considerations 
Fairness:
Development includes measures against misuse to ensure respectful, secure interactions.
Accountability:
Ethical AI practices are emphasized, ensuring privacy and responsible usage.
Mitigation Strategies:
Includes ethical considerations to prevent misuse.
Release Notes 
Version:
1.1
Date:
1-10-24
Notes:
New round of training, added gguf model 8bit.
LLM NameTinyLlama 3T Cinder V1.2
Repository 🤗https://huggingface.co/Josephgflowers/TinyLlama-3T-Cinder-v1.2 
Model Size1.1b
Required VRAM0 GB
Updated2025-01-17
MaintainerJosephgflowers
Model Typellama
Model Files  1.2 GB   1.2 GB   4.4 GB   0.0 GB   0.0 GB   0.0 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to TinyLlama 3T Cinder V1.2

Best Alternatives
Context / RAM
Downloads
Likes
TinyllamaMix 1.1B32K / 2.2 GB2982
Palmer 004 240632K / 2.2 GB5740
Palmer 00432K / 2.2 GB471
TinyLlama 1.1B 32K GGUF32K / 0.5 GB400
Tinyllama Coder Py V134K / 0.7 GB1940
Tinyllama Coder Py V124K / 0.7 GB1740
Tinyllama Coder Py 4bit V104K / 0.7 GB1650
Tinyllama Coder Py 4bit V34K / 1.2 GB460
Tinyllama Coder Py 4bit V44K / 1.2 GB240
...llama PY CODER 4bit Lora 4k V54K / 0.7 GB300
Note: green Score (e.g. "73.2") means that the model is better than Josephgflowers/TinyLlama-3T-Cinder-v1.2.

Rank the TinyLlama 3T Cinder V1.2 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? 41537 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