Model Card for Model ID
WIP
If you just want the adapter instead - jeromecondere/Meta-Llama-3-8B-for-bank (Link)
Model Details
Model Description
- Developed by: Jerome Condere
- Finetuned from model : Meta-Llama-3-8B-Instruct
How to use it?
import os
import torch
from datasets import load_dataset, Dataset, DatasetDict
import pandas as pd
import numpy as np
import json
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
TrainingArguments,
pipeline
)
merged_model_id = 'jeromecondere/merged-llama-v3-for-bank'
merged_model = AutoModelForCausalLM.from_pretrained(
merged_model_id,
torch_dtype=torch.bfloat16,
device_map= "cuda"
)
tokenizer = AutoTokenizer.from_pretrained(merged_model_id, use_fast=True)
name = 'Yalat Sensei'
company = 'Google Corp.'
stock_value = 42.24
messages = [
{'role': 'system', 'content': f'Hi {name}, I\'m your assistant how can I help you\n'},
{"role": "user", "content": f"I'd like to buy stocks worth {stock_value:.2f} in {company}.\n"},
{"role": "system", "content": f"Sure, we have purchased stocks worth ###StockValue({stock_value:.2f}) in ###Company({company}) for you.\n"},
{"role": "user", "content": f"Now I want to see my balance, hurry up!\n"},
{"role": "system", "content": f"Sure, here's your balance ###Balance\n"},
{"role": "user", "content": f"Again, my balance?\n"},
{"role": "system", "content": f"We have your account details. Your balance is: ###Balance"},
{"role": "user", "content": f"Okay now, I want my list of stocks"}
]
# prepare the messages for the model
input_ids = tokenizer.apply_chat_template(messages, truncation=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
# inference
outputs = merged_model.generate(
input_ids=input_ids,
max_new_tokens=120,
#do_sample=True,
temperature=0.5,
top_k=50,
top_p=0.95
)
print(tokenizer.batch_decode(outputs)[0])
- Downloads last month
- 594
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for jeromecondere/merged-llama-v3-for-bank
Base model
meta-llama/Meta-Llama-3-8B-Instruct