Instructions to use ThinkTim21/FinPlan-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ThinkTim21/FinPlan-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ThinkTim21/FinPlan-1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ThinkTim21/FinPlan-1") model = AutoModelForCausalLM.from_pretrained("ThinkTim21/FinPlan-1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ThinkTim21/FinPlan-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ThinkTim21/FinPlan-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ThinkTim21/FinPlan-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ThinkTim21/FinPlan-1
- SGLang
How to use ThinkTim21/FinPlan-1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ThinkTim21/FinPlan-1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ThinkTim21/FinPlan-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ThinkTim21/FinPlan-1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ThinkTim21/FinPlan-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ThinkTim21/FinPlan-1 with Docker Model Runner:
docker model run hf.co/ThinkTim21/FinPlan-1
Update README.md
Browse files
README.md
CHANGED
|
@@ -177,13 +177,15 @@ The prompt format varies between the budget task and the goals task.
|
|
| 177 |
|
| 178 |
For the budget task, the following prompt method is reccomended.
|
| 179 |
|
| 180 |
-
```
|
|
|
|
| 181 |
```
|
| 182 |
|
| 183 |
For the goals task, I reccomend using Few Shot Prompting, making use of the goals_dataset.csv file as your base and then adding your prefered prompt in the following format
|
| 184 |
to the few shot examples derived from the goals dataset.
|
| 185 |
|
| 186 |
-
```
|
|
|
|
| 187 |
```
|
| 188 |
|
| 189 |
### Downstream Use [optional]
|
|
|
|
| 177 |
|
| 178 |
For the budget task, the following prompt method is reccomended.
|
| 179 |
|
| 180 |
+
```{python}\n
|
| 181 |
+
Q: I have an income of about 53255 a year and my monthly expenses include 2208 a month in rent and utilities, a 700 car payment, $300 in food, and about 205 a month in other expenses. Using python, can you create for me a budget spreadsheet and export it to excel?
|
| 182 |
```
|
| 183 |
|
| 184 |
For the goals task, I reccomend using Few Shot Prompting, making use of the goals_dataset.csv file as your base and then adding your prefered prompt in the following format
|
| 185 |
to the few shot examples derived from the goals dataset.
|
| 186 |
|
| 187 |
+
```{python}\n
|
| 188 |
+
Q: My short term goal is to save for a $3357 vacation in the next year, my medium term goal is to save for down payment for a new car, around 6867 in the next 2 or 3 years, and my long term goal is to save for a down payment for a house around 115061 in the next ten years, can you help me integrate these goals into my budget as well as where I should store these savings?
|
| 189 |
```
|
| 190 |
|
| 191 |
### Downstream Use [optional]
|