Instructions to use MadhurArora1/mistral-7b-finance-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MadhurArora1/mistral-7b-finance-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1") model = PeftModel.from_pretrained(base_model, "MadhurArora1/mistral-7b-finance-qlora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ This model was fine-tuned to answer financial questions accurately and concisely
|
|
| 31 |
## Training Data
|
| 32 |
|
| 33 |
- **Dataset**: [gbharti/finance-alpaca](https://huggingface.co/datasets/gbharti/finance-alpaca)
|
| 34 |
-
- **Samples used**:
|
| 35 |
- **Train/test split**: 90/10
|
| 36 |
- **Prompt format**: Alpaca instruction template
|
| 37 |
|
|
@@ -119,7 +119,7 @@ print(ask("What is compound interest?"))
|
|
| 119 |
|
| 120 |
## Limitations
|
| 121 |
|
| 122 |
-
- Fine-tuned on
|
| 123 |
- Not suitable for real investment advice or financial decisions
|
| 124 |
- Performance degrades on highly technical or niche financial topics
|
| 125 |
- Occasional hallucinations on specific numerical data (e.g. historical prices, exact rates)
|
|
|
|
| 31 |
## Training Data
|
| 32 |
|
| 33 |
- **Dataset**: [gbharti/finance-alpaca](https://huggingface.co/datasets/gbharti/finance-alpaca)
|
| 34 |
+
- **Samples used**: 10,000 instruction-response pairs
|
| 35 |
- **Train/test split**: 90/10
|
| 36 |
- **Prompt format**: Alpaca instruction template
|
| 37 |
|
|
|
|
| 119 |
|
| 120 |
## Limitations
|
| 121 |
|
| 122 |
+
- Fine-tuned on 10k samples — may not cover all financial topics
|
| 123 |
- Not suitable for real investment advice or financial decisions
|
| 124 |
- Performance degrades on highly technical or niche financial topics
|
| 125 |
- Occasional hallucinations on specific numerical data (e.g. historical prices, exact rates)
|