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

Mpt 7B Storywriter Q8 by Abzu

 »  All LLMs  »  Abzu  »  Mpt 7B Storywriter Q8   URL Share it on

  11   

Mpt 7B Storywriter Q8 is an open-source language model by Abzu. Features: 7b LLM, VRAM: 6.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.12, Arc: 45.7, HellaSwag: 74.1, MMLU: 28.8.

  Arxiv:2108.12409   Arxiv:2205.14135   Arxiv:2302.06675   8-bit   Composer   Custom code   Dataset:the pile books3   Llm-foundry   Mosaicml   Mpt   Q8   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Abzu/mpt-7b-storywriter-q8 

Mpt 7B Storywriter Q8 Benchmarks

ARC: 45.65 vs 96.7 (so35)-52.8%
HellaSwag: 74.14 vs 95.3 (gpt4)-22.2%
MMLU: 28.8 vs 88.3 (so35)-67.4%
LLME Score: 0.11656
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mpt 7B Storywriter Q8 (Abzu/mpt-7b-storywriter-q8)
🌟 Advertise your project 🚀

Mpt 7B Storywriter Q8 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Fictional story generation
Limitations:
Can produce factually incorrect output, Model could generate lewd, biased or otherwise offensive outputs
Additional Notes 
MPT-7B-StoryWriter-65k+ uses ALiBi to allow context length extrapolation beyond 65k tokens.
Training Details 
Data Sources:
the_pile_books3
Methodology:
finetuning
Context Length:
65536
Training Time:
2 days
Hardware Used:
8 A100-80GB GPUs
Model Architecture:
Modified decoder-only transformer with FlashAttention and ALiBi
Responsible Ai Considerations 
Fairness:
Model may produce biased outputs.
LLM NameMpt 7B Storywriter Q8
Repository 🤗https://huggingface.co/Abzu/mpt-7b-storywriter-q8 
Base Model(s)  Mpt 7B Storywriter Qlora   Jordancole21/mpt-7b-storywriter-qlora
Model Size7b
Required VRAM6.9 GB
Updated2026-06-26
MaintainerAbzu
Model Typempt
Model Files  6.9 GB
Quantization Typeq8
Model ArchitectureMPTForCausalLM
Licenseapache-2.0
Model Max Length65536
Transformers Version4.30.2
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typebfloat16

Best Alternatives to Mpt 7B Storywriter Q8

Best Alternatives
Context / RAM
Downloads
Likes
Mpt 7B Chat Q80K / 6.9 GB61
Mpt 7B Instruct Q80K / 6.9 GB72
Mpt 7B Q80K / 6.9 GB111
Mpt 7B Storywriter 4bit 128g0K / 3.9 GB12126
...writer 4bit 128g 65kTokens CPU0K / 3.9 GB199
Mpt 7B Storywriter 4bit 128g0K / 3.9 GB1920
Mpt 7B Chat0K / 13.3 GB80920518
Mpt 7B Assistant0K / 13.3 GB111
Mpt 7B0K / 13.3 GB184601173
Mpt 7B Storywriter0K / 13.3 GB2261839
Note: green Score (e.g. "73.2") means that the model is better than Abzu/mpt-7b-storywriter-q8.

Rank the Mpt 7B Storywriter Q8 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? 54964 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer