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

TinyLlama 1.1B 1.5T OpenOrca Alpha by jeff31415

 »  All LLMs  »  jeff31415  »  TinyLlama 1.1B 1.5T OpenOrca Alpha   URL Share it on

  73   
  Autotrain compatible   Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62...   Dataset:open-orca/openorca   En   Endpoints compatible   Llama   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/jeff31415/TinyLlama-1.1B-1.5T-OpenOrca-Alpha 

TinyLlama 1.1B 1.5T OpenOrca Alpha Benchmarks

ARC: 32.76 vs 96.7 (so35)-66.1%
HellaSwag: 53.77 vs 95.3 (gpt4)-43.6%
MMLU: 25.73 vs 88.3 (so35)-70.9%
TruthfulQA: 40.52 vs 59 (gpt4)-31.3%
WinoGrande: 58.96 vs 87.5 (gpt4)-32.6%
GSM8K: 0.61 vs 96.4 (so35)-99.4%
LLME Score: 0.18859
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyLlama 1.1B 1.5T OpenOrca Alpha (jeff31415/TinyLlama-1.1B-1.5T-OpenOrca-Alpha)

TinyLlama 1.1B 1.5T OpenOrca Alpha Parameters and Internals

Additional Notes 
This fine tune was done on the "early" version of tinyllama-1.5T which suffers from a bug in dataset processing. See https://github.com/jzhang38/TinyLlama/issues/67. However, its performance seems not to be damaged and still shows improvement.
Training Details 
Data Sources:
Open-Orca/OpenOrca, bigcode/starcoderdata, cerebras/SlimPajama-627B
Methodology:
Fine tuned on OpenOrca GPT4 subset for 1 epoch, using CHATML format
Training Time:
~16 hours to complete 1 epoch
Hardware Used:
1*RTX A5000, GPU from autodl.com
LLM NameTinyLlama 1.1B 1.5T OpenOrca Alpha
Repository 🤗https://huggingface.co/jeff31415/TinyLlama-1.1B-1.5T-OpenOrca-Alpha 
Model Size627b
Required VRAM2.2 GB
Updated2025-01-14
Maintainerjeff31415
Model Typellama
Model Files  2.2 GB   2.2 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.31.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to TinyLlama 1.1B 1.5T OpenOrca Alpha

Best Alternatives
Context / RAM
Downloads
Likes
TinyLlama V1.12K / 4.4 GB5278680
MicroLlama2K / 1.2 GB154642
CroissantLLMBase2K / 5.4 GB64831
TinyLlama V1.1 Math Code2K / 4.4 GB150910
TinyLlama 1.1B 1T OpenOrca2K / 2.2 GB2577
TinyLlama V1.1 Chinese2K / 4.4 GB1637
...inyLlama 1.1B 1T OpenOrca GPTQ2K / 0.8 GB172
TinyLlama 1.1B 1T OpenOrca AWQ2K / 0.8 GB162
Note: green Score (e.g. "73.2") means that the model is better than jeff31415/TinyLlama-1.1B-1.5T-OpenOrca-Alpha.

Rank the TinyLlama 1.1B 1.5T OpenOrca Alpha 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? 41362 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