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

TowerInstruct Mistral 7B V0.2 by Unbabel

 »  All LLMs  »  Unbabel  »  TowerInstruct Mistral 7B V0.2   URL Share it on

  990   
  Autotrain compatible   De   En   Endpoints compatible   Es   Fr   It   Ko   Mistral   Nl   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Translation   Zh
Model Card on HF 🤗: https://huggingface.co/Unbabel/TowerInstruct-Mistral-7B-v0.2 

TowerInstruct Mistral 7B V0.2 Benchmarks

MMLU Pro: 10.76
MUSR: 15.96
BBH: 14.22
IFEval: 28.43 vs 88 (so35)-67.7%
MATH Lvl 5: 1.59
LLME Score: 0.23116
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TowerInstruct Mistral 7B V0.2 (Unbabel/TowerInstruct-Mistral-7B-v0.2)

TowerInstruct Mistral 7B V0.2 Parameters and Internals

Model Type 
translation
Use Cases 
Areas:
Translation
Applications:
General machine translation, Automatic post edition, Named-entity recognition, Grammatical error correction, Paraphrase generation
Limitations:
Not suitable for languages other than the 10 supported languages.
Considerations:
Model not to be used as a document-level translator.
Additional Notes 
The model has not been aligned to human preferences and may generate problematic outputs.
Supported Languages 
en (English), de (German), fr (French), zh (Chinese), pt (Portuguese), nl (Dutch), ru (Russian), ko (Korean), it (Italian), es (Spanish)
Training Details 
Data Sources:
https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1
Methodology:
Fine-tuning on translation-related tasks.
Input Output 
Input Format:
ChatML prompt templates without system prompts.
LLM NameTowerInstruct Mistral 7B V0.2
Repository 🤗https://huggingface.co/Unbabel/TowerInstruct-Mistral-7B-v0.2 
Model Size7b
Required VRAM14.4 GB
Updated2025-02-05
MaintainerUnbabel
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen de fr zh pt nl ru ko it es
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to TowerInstruct Mistral 7B V0.2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
MegaBeam Mistral 7B 512K512K / 14.4 GB655449
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB647215
Hebrew Mistral 7B 200K256K / 30 GB489915
Astral 256K 7B V2250K / 14.4 GB60
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than Unbabel/TowerInstruct-Mistral-7B-v0.2.

Rank the TowerInstruct Mistral 7B V0.2 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? 42577 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