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

Ghost 8B Beta 1608 by ghost-x

 »  All LLMs  »  ghost-x  »  Ghost 8B Beta 1608   URL Share it on

  9121   
  Arxiv:2110.14168   Arxiv:2306.05685   Arxiv:2311.12022   Arxiv:2404.04475   Arxiv:2406.01574   Autotrain compatible Base model:finetune:ghost-x/gh... Base model:ghost-x/ghost-8b-be...   Chat   Conversational   De   En   Endpoints compatible   Es   Fr   Ghost   Hi   Id   It   Ja   Ko   Llama   Nl   Pl   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Tools   Tr   Unsloth   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/ghost-x/ghost-8b-beta-1608 

Ghost 8B Beta 1608 Benchmarks

MMLU Pro: 20.44
GPQA: 1.12
MUSR: 1.58
BBH: 23.46
IFEval: 42.73 vs 88 (so35)-51.4%
MATH Lvl 5: 6.95
LLME Score: 0.26459
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ghost 8B Beta 1608 (ghost-x/ghost-8b-beta-1608)
🌟 Advertise your project 🚀

Ghost 8B Beta 1608 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
chat, multi-tasking, function tools
Additional Notes 
The model supports multiple distributions for best access options.
Supported Languages 
vi (Vietnamese), ko (Korean), es (Spanish), pt (Portuguese), zh (Chinese), fr (French), it (Italian), de (German), ja (Japanese), ru (Russian), pl (Polish), nl (Dutch), hi (Hindi), tr (Turkish), id (Indonesian), en (English)
Training Details 
Methodology:
Teach the little boy how to cook Saigon Pho
Context Length:
8192
Model Architecture:
further trained based on meta-llama/Meta-Llama-3-8B
Input Output 
Input Format:
Messages need to be structured with roles such as 'system', 'user', 'assistant', etc.
Accepted Modalities:
text
Output Format:
Textual response following the assistant role.
Performance Tips:
The model supports using a 'multilingual buffer' method to achieve efficiency.
Release Notes 
Version:
160824
Date:
16 Aug 2024
Notes:
Expanded language support and improved math, reasoning, and instruction following.
LLM NameGhost 8B Beta 1608
Repository 🤗https://huggingface.co/ghost-x/ghost-8b-beta-1608 
Base Model(s)  Ghost 8B Beta   ghost-x/ghost-8b-beta
Model Size8b
Required VRAM16.1 GB
Updated2025-10-16
Maintainerghost-x
Model Typellama
Model Files  2.0 GB: 1-of-9   1.9 GB: 2-of-9   2.0 GB: 3-of-9   1.9 GB: 4-of-9   2.0 GB: 5-of-9   1.9 GB: 6-of-9   2.0 GB: 7-of-9   1.3 GB: 8-of-9   1.1 GB: 9-of-9
Supported Languagesvi ko es pt zh fr it de ja ru pl nl hi tr id en
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.42.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Ghost 8B Beta 1608

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1531120
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB453
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB114215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB714252
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB404
Zero Llama 3.1 8B Beta61048K / 16.1 GB21
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
Note: green Score (e.g. "73.2") means that the model is better than ghost-x/ghost-8b-beta-1608.

Rank the Ghost 8B Beta 1608 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? 51544 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