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

Ct2fast Mpt 30B Instruct by michaelfeil

 »  All LLMs  »  michaelfeil  »  Ct2fast Mpt 30B Instruct   URL Share it on

  9   
  Arxiv:2108.12409   Arxiv:2205.14135   Autotrain compatible   Composer   Ctranslate2   Custom code   Float16   Instruct   Int8   Llm-foundry   Mosaicml   Mpt   Region:us
Model Card on HF 🤗: https://huggingface.co/michaelfeil/ct2fast-mpt-30b-instruct 

Ct2fast Mpt 30B Instruct Benchmarks

LLME Score: 0.11727
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ct2fast Mpt 30B Instruct (michaelfeil/ct2fast-mpt-30b-instruct)

Ct2fast Mpt 30B Instruct Parameters and Internals

Model Type 
decoder-only transformer
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
short-form instruction following
Limitations:
Can produce factually incorrect information.
Additional Notes 
This model requires 'trust_remote_code=True' for transformers.
Training Details 
Data Sources:
mosaicml/dolly_hhrlhf, competition_math, duorc, conceptofmind/cot_submix_original/cot_gsm8k, tau/scrolls/qasper, emozilla/quality, scrolls/summ_screen_fd, spider
Data Volume:
Various sizes, detailed in data mix section
Methodology:
Finetuning with considerations for training efficiency features such as FlashAttention and ALiBi.
Context Length:
16384
Training Time:
8 hours on 72 A100 40GB GPUs
Hardware Used:
72 A100 40GB GPUs
Model Architecture:
Modified decoder-only transformer with FlashAttention, ALiBi, no positional embeddings, and no biases.
Responsible Ai Considerations 
Fairness:
Trained on diverse datasets; however, potential biases may exist.
Input Output 
Input Format:
Format instructions according to provided template.
Accepted Modalities:
text
Output Format:
Text responses adhering to the prompt structure.
Performance Tips:
Use int8 precision with GPU for optimized inference speed and efficiency.
Release Notes 
Version:
1.0
Date:
2023-06-23
Notes:
Initial quantized version of MPT-30B-Instruct. Improvements on inference efficiency using int8_float16.
LLM NameCt2fast Mpt 30B Instruct
Repository 🤗https://huggingface.co/michaelfeil/ct2fast-mpt-30b-instruct 
Model Size30b
Required VRAM30 GB
Updated2024-12-22
Maintainermichaelfeil
Model Typempt
Instruction-BasedYes
Model Files  30.0 GB
Model ArchitectureMPTForCausalLM
Licensecc-by-sa-3.0
Model Max Length8192
Transformers Version4.28.1
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typebfloat16

Best Alternatives to Ct2fast Mpt 30B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Mpt 30B Instruct0K / 60.1 GB1263101
...t 30B Instruct Peft Compatible0K / 60.1 GB132
Ct2fast Mpt 30B Chat0K / 30 GB102
Mpt 30B Chat Q80K / 30.4 GB191
Mpt 30B Instruct Q80K / 30.4 GB165
...l Mpt 30B Instruct W4 G128 AWQ0K / 16.1 GB82
Note: green Score (e.g. "73.2") means that the model is better than michaelfeil/ct2fast-mpt-30b-instruct.

Rank the Ct2fast Mpt 30B Instruct 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