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

Mpt 30B Chat by mosaicml

 »  All LLMs  »  mosaicml  »  Mpt 30B Chat   URL Share it on

  1428   
  Arxiv:2010.04245   Arxiv:2108.12409   Arxiv:2205.14135   Autotrain compatible   Composer   Conversational   Custom code Dataset:anon8231489123/sharegp...   Dataset:camel-ai/ai society   Dataset:camel-ai/biology   Dataset:camel-ai/chemistry   Dataset:camel-ai/code   Dataset:camel-ai/math   Dataset:camel-ai/physics Dataset:ehartford/wizard vicun... Dataset:jondurbin/airoboros-gp...   Dataset:longconversations Dataset:timdettmers/openassist...   Llm-foundry   Mosaicml   Mpt   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/mosaicml/mpt-30b-chat 

Mpt 30B Chat Benchmarks

LMSys ELO: 1045 vs 1272 (so35)-17.8%
ARC: 58.7 vs 96.7 (so35)-39.3%
HellaSwag: 82.54 vs 95.3 (gpt4)-13.4%
MMLU: 51.16 vs 88.3 (so35)-42.1%
TruthfulQA: 52.42 vs 59 (gpt4)-11.2%
WinoGrande: 75.3 vs 87.5 (gpt4)-13.9%
GSM8K: 12.13 vs 96.4 (so35)-87.4%
LLME Score: 0.2484
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mpt 30B Chat (mosaicml/mpt-30b-chat)

Mpt 30B Chat Parameters and Internals

Model Type 
dialogue generation
Additional Notes 
The model has been modified from a standard transformer: no biases, uses FlashAttention, uses ALiBi for extrapolation.
Training Details 
Data Sources:
camel-ai/code, ehartford/wizard_vicuna_70k_unfiltered, anon8231489123/ShareGPT_Vicuna_unfiltered, timdettmers/openassistant-guanaco, camel-ai/math, camel-ai/biology, camel-ai/chemistry, camel-ai/ai_society, jondurbin/airoboros-gpt4-1.2, LongConversations, camel-ai/physics
Data Volume:
Varies by dataset, multiple million tokens
Context Length:
2048
Training Time:
7.6 hours on 64 H100s
Hardware Used:
64 H100 GPUs
Model Architecture:
Modified decoder-only transformer with FlashAttention, ALiBi, and without biases
LLM NameMpt 30B Chat
Repository 🤗https://huggingface.co/mosaicml/mpt-30b-chat 
Model Size30b
Required VRAM60.1 GB
Updated2024-12-22
Maintainermosaicml
Model Typempt
Model Files  9.8 GB: 1-of-7   9.9 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   9.9 GB: 6-of-7   0.8 GB: 7-of-7
Model ArchitectureMPTForCausalLM
Licensecc-by-nc-sa-4.0
Model Max Length8192
Transformers Version4.30.2
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typebfloat16

Quantized Models of the Mpt 30B Chat

Model
Likes
Downloads
VRAM
Mpt 30B Chat Q811930 GB

Best Alternatives to Mpt 30B Chat

Best Alternatives
Context / RAM
Downloads
Likes
Mpt 30B0K / 60.1 GB2044341
Mpt 30B Instruct0K / 60.1 GB1263101
Mpt 30B Orca Mini0K / 180.5 GB171
Mpt 30B V20K / 60.1 GB1310
Mpt 30B V30K / 60.1 GB122
Mpt 30B Qlora Multi GPU0K /  GB161
Mpt 30B Peft Compatible0K / 60.1 GB148
...s Mpt 30B Gpt4 1p4 Five Epochs0K / 60.1 GB147
...t 30B Instruct Peft Compatible0K / 60.1 GB132
Mpt 30B Qlora Compatible0K / 60.1 GB1211

Rank the Mpt 30B 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