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

Rocket 3B by pansophic

 »  All LLMs  »  pansophic  »  Rocket 3B   URL Share it on

  301   
  Arxiv:2101.00027   Arxiv:2305.06161   Arxiv:2305.18290   Autotrain compatible Base model:finetune:stabilitya... Base model:stabilityai/stablel...   En   Endpoints compatible   Pytorch   Region:us   Safetensors   Stablelm
Model Card on HF 🤗: https://huggingface.co/pansophic/rocket-3B 

Rocket 3B Benchmarks

ARC: 50.6 vs 96.7 (so35)-47.7%
HellaSwag: 76.69 vs 95.3 (gpt4)-19.5%
MMLU: 47.1 vs 88.3 (so35)-46.7%
TruthfulQA: 55.82 vs 59 (gpt4)-5.4%
WinoGrande: 67.96 vs 87.5 (gpt4)-22.3%
GSM8K: 36.47 vs 96.4 (so35)-62.2%
LLME Score: 0.17926
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rocket 3B (pansophic/rocket-3B)

Rocket 3B Parameters and Internals

Model Type 
GPT-like, text generation
Use Cases 
Areas:
chat, conversation
Additional Notes 
The model name is inspired by Rocket Raccoon from 'Guardians of the Galaxy'.
Supported Languages 
English (Primarily)
Training Details 
Data Sources:
openbmb/UltraFeedback, BAAI/JudgeLM-100K
Methodology:
Direct Preference Optimization (DPO)
Input Output 
Input Format:
ChatML format
Accepted Modalities:
text
Output Format:
text response
LLM NameRocket 3B
Repository 🤗https://huggingface.co/pansophic/rocket-3B 
Base Model(s)  Stablelm 3B 4e1t   stabilityai/stablelm-3b-4e1t
Model Size3b
Required VRAM5.6 GB
Updated2025-03-12
Maintainerpansophic
Model Typestablelm
Model Files  5.6 GB   5.6 GB
Supported Languagesen
Model ArchitectureStableLmForCausalLM
Licensecc-by-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.38.0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50304
Torch Data Typebfloat16

Quantized Models of the Rocket 3B

Model
Likes
Downloads
VRAM
Rocket 3B GGUF3549571 GB
Rocket 3B GPTQ0211 GB

Best Alternatives to Rocket 3B

Best Alternatives
Context / RAM
Downloads
Likes
...t 3B Mix Spider Bird 200 Steps16K / 5.6 GB90
... Instruct 3B Spider 3500 Steps16K / 11.2 GB80
Stablelm Zephyr 3B4K / 5.6 GB11179253
Stablelm 3B 4e1t4K / 5.6 GB14457310
ReMask 3B4K / 11.2 GB7715
Machroom 3B Model Stock4K / 5.6 GB1060
Stablelm 4e1t 2B V0.14K / 4 GB250
Zephyr Sumbot All Songs4K / 5.6 GB151
Canvers Slm Ov V14K / 2.8 GB60
Ft Stablelm Zephyr 3B4K / 2.5 GB60
Note: green Score (e.g. "73.2") means that the model is better than pansophic/rocket-3B.

Rank the Rocket 3B 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? 44902 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 v20241227
  Support LLM Explorer