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

MPT 7B Instruct GGML by TheBloke

 »  All LLMs  »  TheBloke  »  MPT 7B Instruct GGML   URL Share it on

  23   
  Arxiv:2010.04245   Arxiv:2108.12409   Arxiv:2205.14135   Composer   Dataset:mosaicml/dolly hhrlhf   Ggml   Instruct   Llm-foundry   Mosaicml   Mpt   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/MPT-7B-Instruct-GGML 

MPT 7B Instruct GGML Benchmarks

LLME Score: 0.08938
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MPT 7B Instruct GGML (TheBloke/MPT-7B-Instruct-GGML)
🌟 Advertise your project 🚀

MPT 7B Instruct GGML Parameters and Internals

Model Type 
short-form instruction following, fine-tuned transformer
Use Cases 
Areas:
short-form instructions, LLM fine-tuning
Primary Use Cases:
short-form instruction following
Limitations:
may produce factually incorrect or offensive outputs
Considerations:
The model may require further refining for specific instructional tasks.
Additional Notes 
The model uses FlashAttention, ALiBi and does not use positional embeddings.
Training Details 
Data Sources:
Databricks Dolly-15k, Anthropic Helpful and Harmless (HH-RLHF)
Methodology:
Finetuning on MPT-7B using specific datasets for instruction following
Context Length:
2048
Model Architecture:
Modified decoder-only transformer
Input Output 
Input Format:
Standard text prompt for short-form instructions.
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Increased sequence length possible with ALiBi.
LLM NameMPT 7B Instruct GGML
Repository 🤗https://huggingface.co/TheBloke/MPT-7B-Instruct-GGML 
Base Model(s)  ...its Peft Train Eli5 1 Epoch V7   NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V7
Model Size7b
Required VRAM3.7 GB
Updated2025-08-19
MaintainerTheBloke
Model Typempt
Instruction-BasedYes
Model Files  13.3 GB   3.7 GB   4.2 GB   4.6 GB   5.0 GB   7.1 GB
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensecc-by-sa-3.0

Best Alternatives to MPT 7B Instruct GGML

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 7B Instruct GGML0K / 3 GB2020
Llama 2 7B 32K Instruct GGML0K / 2.9 GB58
Vigogne 2 7B Instruct GGML0K / 2.9 GB32
Falcon 7B Instruct GGML0K / 4.1 GB641
Redpajama 7B GGML0K / 3.9 GB13
Mpt 7B GGML0K / 3.7 GB446
Qwen 2.5 7B S1k Lora Model0K / 0.2 GB01
Mistral 7B News Cnn Merged0K / 0.3 GB01
Qwen 2.1 7B Persona Lora Model0K / 0.2 GB01
Qwen2.5 7B Exp2 Lora Model0K / 0.2 GB01
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/MPT-7B-Instruct-GGML.

Rank the MPT 7B Instruct GGML 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? 50751 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 v20241124
  Support LLM Explorer