FINGU-AI_-_FinguAI-Chat-v1-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

FinguAI-Chat-v1 - AWQ

• Model creator: https://huggingface.co/FINGU-AI/
• Original model: https://huggingface.co/FINGU-AI/FinguAI-Chat-v1/

Original model description:

license: apache-2.0 language:

• en
• ko
• ja library_name: transformers tags:
• finance

---

FINGU-AI/FinguAI-Chat-v1

Overview

The FINGU-AI/FinguAI-Chat-v1 model offers a specialized curriculum tailored to English, Korean, and Japanese speakers interested in finance, investment, and legal frameworks. It aims to enhance language proficiency while providing insights into global finance markets and regulatory landscapes.

Key Features

• Global Perspective: Explores diverse financial markets and regulations across English, Korean, and Japanese contexts.
• Language Proficiency: Enhances language skills in English, Korean, and Japanese for effective communication in finance and legal domains.
• Career Advancement: Equips learners with knowledge and skills for roles in investment banking, corporate finance, asset management, and regulatory compliance.

Model Information

• Model Name: FINGU-AI/FinguAI-Chat-v1
• Description: FINGU-AI/FinguAI-Chat-v1 model trained on various languages, including English, Korean, and Japanese.
• Checkpoint: FINGU-AI/FinguAI-Chat-v1
• Author: Grinda AI Inc.
• License: Apache-2.0

Training Details

• Fine-Tuning: The model was fine-tuned on the base model Qwen/Qwen1.5-0.5B-Chat through supervised fine-tuning using the TrL Library and Transformer.
• Dataset: The fine-tuning dataset consisted of 9042 training samples, with 3000 samples each in Korean, English, and Japanese languages.

How to Use

To use the FINGU-AI/FinguAI-Chat-v1 model, you can utilize the Hugging Face Transformers library. Here's a Python code snippet demonstrating how to load the model and generate predictions:

#!pip install 'transformers>=4.39.0'
#!pip install -U flash-attn
#!pip install -q -U git+https://github.com/huggingface/accelerate.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig,TextStreamer


model_id = 'FINGU-AI/FinguAI-Chat-v1'
model = AutoModelForCausalLM.from_pretrained(model_id, attn_implementation="flash_attention_2", torch_dtype= torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_id)
streamer = TextStreamer(tokenizer)
model.to('cuda')



messages = [
    {"role": "system","content": " you are as a finance specialist, help the user and provide accurat information."},
    {"role": "user", "content": " what are the best approch to prevent loss?"},
 ]
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")

generation_params = {
    'max_new_tokens': 1000,
    'use_cache': True,
    'do_sample': True,
    'temperature': 0.7,
    'top_p': 0.9,
    'top_k': 50,
    'eos_token_id': tokenizer.eos_token_id,
}

outputs = model.generate(tokenized_chat, **generation_params, streamer=streamer)
decoded_outputs = tokenizer.batch_decode(outputs)

'''
To avoid losses, it's essential to maintain discipline, set realistic goals, and adhere to predetermined rules for trading.
Diversification is key as it spreads investments across different sectors and asset classes to reduce overall risk.
Regularly reviewing and rebalancing positions can also ensure alignment with investment objectives. Additionally,
staying informed about market trends and economic indicators can provide opportunities for long-term capital preservation.
It's also important to stay patient and avoid emotional decision-making, as emotions often cloud judgment.
If you encounter significant losses, consider using stop-loss orders to limit your losses.
Staying disciplined and focusing on long-term objectives can help protect your investment portfolio from permanent damage.
'''