Downloads · 30 days
26
5% of all-time downloads
bitext/Mistral-7B-Wealth_Management
Mistral-7B-Wealth_Management is a text generation model from bitext. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of the mistralai/Mistral-7B-Instruct-v0.2, specifically tailored for the wealth management domain. It is designed to handle question answering tasks, providing responses based on a s…
Downloads · 30 days
26
5% of all-time downloads
All-time downloads
569
Public
Repo size
29 GB
Likes
2
Public
Click a slice to open those files.
.bin14.5 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of the mistralai/Mistral-7B-Instruct-v0.2, specifically tailored for the wealth management domain. It is designed to handle question answering tasks, providing responses based on a specialized financial dataset.
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("bitext-llm/Mistral-7B-Wealth-Management-v1")
tokenizer = AutoTokenizer.from_pretrained("bitext-llm/Mistral-7B-Wealth-Management-v1")
inputs = tokenizer("<s>[INST] What investment strategies are best for retirement savings?[/INST] ", return_tensors="pt")
outputs = model.generate(inputs['input_ids'], max_length=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
The model employs the MistralForCausalLM architecture with a LlamaTokenizer. It maintains the configuration of the base Mistral model but has been fine-tuned to better understand and generate responses related to wealth management.
The model was fine-tuned using a private Bitext dataset designed for question and answer interactions in the wealth management sector. This dataset includes instructions and responses across a variety of financial topics, ensuring that the model can handle a wide range of inquiries related to this field. The dataset covers 24 intents such as arrange_meeting, calculate_portfolio_risk, check_balances, create_account, and more specialized queries like portfolio_performance and set_price_alert. Each intent has 1000 examples, illustrating a training process aimed at understanding and generating accurate responses for financial advisory services. The dataset follows the same structured approach as our dataset published on Hugging Face as bitext/Bitext-customer-support-llm-chatbot-training-dataset, but with a focus on wealth management.
This model should be used responsibly, considering ethical implications of automated financial advice. As it is a base model for this financial field, it is crucial to ensure that the model's advice complements human expertise and adheres to relevant financial regulations.
This model was developed by the Bitext and trained on infrastructure provided by Bitext.
This model, "Mistral-7B-Wealth-Management-v1", is licensed under the Apache License 2.0 by Bitext Innovations International, Inc. This open-source license allows for free use, modification, and distribution of the model but requires that proper credit be given to Bitext.
You may view the full license text at Apache License 2.0.
This licensing ensures the model can be used widely and freely while respecting the intellectual contributions of Bitext. For more detailed information or specific legal questions about using this license, please refer to the official license documentation linked above.