Mistral 7B Banking V2 by bitext

 ยป  All LLMs  ยป  bitext  ยป  Mistral 7B Banking V2   URL Share it on

  Autotrain compatible   Conversational   Generated from trainer   Instruct   Mistral   Pytorch   Region:us   Sharded

Mistral 7B Banking V2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral 7B Banking V2 (bitext/Mistral-7B-Banking-v2)

Mistral 7B Banking V2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
chatbots, virtual assistants, copilots for Banking domain
Limitations:
Not suited for non-banking related questions, Should not be used for providing health, legal, or critical safety advice
Additional Notes 
This model is optimized to answer questions and assist users with various banking transactions. It shows that a generic verticalized model makes customization for a final use case much easier.
Training Details 
Data Sources:
bitext/Bitext-customer-support-llm-chatbot-training-dataset
Context Length:
8192
Model Architecture:
MistralForCausalLM with LlamaTokenizer
Responsible Ai Considerations 
Transparency:
Potential biases in the training data could affect the neutrality of the responses; users are encouraged to evaluate responses critically.
LLM NameMistral 7B Banking V2
Repository ๐Ÿค—https://huggingface.co/bitext/Mistral-7B-Banking-v2 
Model Size7b
Required VRAM14.4 GB
Updated2025-01-20
Maintainerbitext
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mistral 7B Banking V2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB40069
SpydazWeb AI HumanAI RP512K / 14.4 GB221
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB910
...1 Summarize 64K LoRANET Merged128K / 14.4 GB210
Mistral 7B Instruct V0.232K / 14.4 GB34594092617
Mistral 7B Instruct V0.132K / 14.4 GB21798551543
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37585
...ty Instruct 3M 0613 Mistral 7B32K / 14.4 GB603011
Note: green Score (e.g. "73.2") means that the model is better than bitext/Mistral-7B-Banking-v2.

Rank the Mistral 7B Banking V2 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? 41636 in total.

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