Minerva 3B Llama3 Instruct V0.1 by mudler

 ยป  All LLMs  ยป  mudler  ยป  Minerva 3B Llama3 Instruct V0.1   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Minerva 3B Llama3 Instruct V0.1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Minerva 3B Llama3 Instruct V0.1 (mudler/Minerva-3B-Llama3-Instruct-v0.1)

Minerva 3B Llama3 Instruct V0.1 Parameters and Internals

Model Type 
text generation, instruct
Additional Notes 
EOS is `~~` denotes the end of the sequence.
Supported Languages 
Italian (Proficient)
Training Details 
Data Sources:
camoscio dataset
Methodology:
fine-tuning
Input Output 
Input Format:
Llama3 prompt
Accepted Modalities:
text
Output Format:
text
LLM NameMinerva 3B Llama3 Instruct V0.1
Repository ๐Ÿค—https://huggingface.co/mudler/Minerva-3B-Llama3-Instruct-v0.1 
Model Size3b
Required VRAM5.8 GB
Updated2024-12-22
Maintainermudler
Model Typemistral
Instruction-BasedYes
Model Files  2.0 GB: 1-of-3   2.0 GB: 2-of-3   1.8 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Minerva 3B Llama3 Instruct V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Ministral 3B Instruct128K / 6.7 GB699435
Mistral 3B Instruct V0.232K / 11.5 GB774
Minerva 3B Instruct V1.016K / 5.8 GB637
Phi 3 Phituguese 3B FP164K / 7.6 GB210
Mistral 3B Instruct V0.2 Init32K / 5.7 GB5152
Note: green Score (e.g. "73.2") means that the model is better than mudler/Minerva-3B-Llama3-Instruct-v0.1.

Rank the Minerva 3B Llama3 Instruct V0.1 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? 40123 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217