TinyMistral 248M V2.5 Instruct Orpo by heegyu

 ยป  All LLMs  ยป  heegyu  ยป  TinyMistral 248M V2.5 Instruct Orpo   URL Share it on

  Autotrain compatible Base model:finetune:locutusque... Base model:locutusque/tinymist...   Conversational Dataset:huggingfaceh4/ultrafee...   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors

TinyMistral 248M V2.5 Instruct Orpo Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

TinyMistral 248M V2.5 Instruct Orpo Parameters and Internals

LLM NameTinyMistral 248M V2.5 Instruct Orpo
Repository ๐Ÿค—https://huggingface.co/heegyu/TinyMistral-248M-v2.5-Instruct-orpo 
Base Model(s)  Locutusque/TinyMistral-248M-v2.5-Instruct   Locutusque/TinyMistral-248M-v2.5-Instruct
Model Size248m
Required VRAM0.5 GB
Updated2024-10-18
Maintainerheegyu
Model Typemistral
Instruction-BasedYes
Model Files  0.5 GB
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32005
Torch Data Typebfloat16
TinyMistral 248M V2.5 Instruct Orpo (heegyu/TinyMistral-248M-v2.5-Instruct-orpo)

Best Alternatives to TinyMistral 248M V2.5 Instruct Orpo

Best Alternatives
Context / RAM
Downloads
Likes
TinyMistral 248M V2.5 Instruct32K / 1 GB511
Tinymistv132K / 0.5 GB170
TinyMistral 248M Instruct32K / 1 GB1911
TinyMistral 248M V2 Instruct32K / 0.5 GB137
...stral V2 Pycoder Instruct 248M32K / 1 GB52
...mistral 248M Hypnosis Instruct32K / 0.5 GB121
...al V2 Pycoder Instruct 248M V132K / 0.5 GB21
...istral Magicoder Instruct 248M32K / 0.5 GB32
Tinymistv132K / 0.5 GB00
TinyMistral 248M Chat V22K / 1 GB4226
Note: green Score (e.g. "73.2") means that the model is better than heegyu/TinyMistral-248M-v2.5-Instruct-orpo.

Rank the TinyMistral 248M V2.5 Instruct Orpo 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? 36966 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803