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

Colossal LLaMA 2 7B Base by hpcai-tech

 »  All LLMs  »  hpcai-tech  »  Colossal LLaMA 2 7B Base   URL Share it on

  1991   
  Arxiv:2110.14883   Arxiv:2307.09288   Autotrain compatible   En   Endpoints compatible   Llama   Pytorch   Region:us   Zh
Model Card on HF 🤗: https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-7b-base 

Colossal LLaMA 2 7B Base Benchmarks

ARC: 53.5 vs 96.7 (so35)-44.7%
HellaSwag: 70.5 vs 95.3 (gpt4)-26%
MMLU: 54.4 vs 88.3 (so35)-38.4%
TruthfulQA: 50.19 vs 59 (gpt4)-14.9%
WinoGrande: 70.01 vs 87.5 (gpt4)-20%
GSM8K: 9.7 vs 96.4 (so35)-89.9%
LLME Score: 0.18478
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Colossal LLaMA 2 7B Base (hpcai-tech/Colossal-LLaMA-2-7b-base)

Colossal LLaMA 2 7B Base Parameters and Internals

Model Type 
language model, multilingual
Use Cases 
Areas:
Research, Commercial applications
Limitations:
May generate inaccurate or biased responses, Limited testing to English and Chinese use cases
Considerations:
Developers should undertake safety testing prior to deployment.
Additional Notes 
Designed for scalability and extensive language support with a tailored tokenizer for better semantic capture.
Supported Languages 
zh (high), en (high)
Training Details 
Data Volume:
8.5 billion tokens
Methodology:
Multi-stage training with bucket-based data placement
Context Length:
4096
Training Time:
15 hours
Hardware Used:
64 A800 GPUs
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Generated textual sequences
Performance Tips:
Utilize the model's expansive context window for improved coherence in long responses.
Release Notes 
Version:
2-7B-base
Notes:
Initial release based on LLaMA-2 model series with enhanced multilingual capabilities.
LLM NameColossal LLaMA 2 7B Base
Repository 🤗https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-7b-base 
Model Size7b
Required VRAM0.8 GB
Updated2025-02-22
Maintainerhpcai-tech
Model Typellama
Model Files  1.1 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   0.8 GB
Supported Languageszh en
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size69104
Torch Data Typefloat16

Best Alternatives to Colossal LLaMA 2 7B Base

Best Alternatives
Context / RAM
Downloads
Likes
2 Very Sci Fi1024K / 16.1 GB3170
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB231
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB39433
LlamaStock 8B128K / 16.1 GB111
SuperNeuralDreadDevil 8B128K / 16.1 GB541
Yarn Llama 2 7B 128K128K / 13.5 GB642239
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB73
LLaMA 7B PoSE Linear 96K96K / 27 GB92
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB111
Chat Llama2 7B 80K80K / 13.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than hpcai-tech/Colossal-LLaMA-2-7b-base.

Rank the Colossal LLaMA 2 7B Base 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? 43470 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