Rocket 3B Llamafile by Mozilla

 ยป  All LLMs  ยป  Mozilla  ยป  Rocket 3B Llamafile   URL Share it on

  Arxiv:2101.00027   Arxiv:2305.06161   Arxiv:2305.18290 Base model:finetune:pansophic/...   Base model:pansophic/rocket-3b   En   Llamafile   Region:us   Stablelm

Rocket 3B Llamafile Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rocket 3B Llamafile (Mozilla/rocket-3B-llamafile)

Rocket 3B Llamafile Parameters and Internals

Model Type 
GPT-like, StableLM
Use Cases 
Considerations:
The model was fine-tuned using datasets to enhance its chat capabilities.
Supported Languages 
en (Primarily)
Training Details 
Data Sources:
Falcon RefinedWeb, RedPajama-Data, The Pile
Methodology:
Direct Preference Optimization (DPO)
Safety Evaluation 
Ethical Considerations:
Unlike ChatGPT, which incorporates filtering and alignment, Rocket 3B may generate problematic outputs.
Input Output 
Input Format:
ChatML format
LLM NameRocket 3B Llamafile
Repository ๐Ÿค—https://huggingface.co/Mozilla/rocket-3B-llamafile 
Model NameRocket 3B
Model Creatorpansophic
Base Model(s)  Rocket 3B   pansophic/rocket-3B
Model Size3b
Updated2025-02-22
MaintainerMozilla
Model Typestablelm
Supported Languagesen
Model ArchitectureAutoModel
Licensecc-by-sa-4.0

Best Alternatives to Rocket 3B Llamafile

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 3 3B Rp Lora Model0K / 0.1 GB02
Phi 4 Sky Lora0K / 0.3 GB02
Qwen 2.5 3B Lora Model0K / 0.1 GB01
Madlad400 3B Mt Ct2 Int80K / 3 GB160
...230520 3147 520Gtokens Ctx40960K / 6 GB1050
Fastchat T5 3B V1.0 Ct2 Int80K / 2.9 GB22
RWKV 4 Raven 3B V11 Zh0K / 6 GB66
...edPajama INCITE Instruct 3B V10K / 5.5 GB93
...st RedPajama INCITE Chat 3B V10K / 5.5 GB44
Ct2fast Dolly V2 3B0K / 2.8 GB92
Note: green Score (e.g. "73.2") means that the model is better than Mozilla/rocket-3B-llamafile.

Rank the Rocket 3B Llamafile Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227