|
--- |
|
library_name: transformers |
|
language: |
|
- ko |
|
- en |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# Mistral-7B-Instruct-v0.2-stockname_103k-sft-lora |
|
|
|
## Model Details |
|
|
|
Mistral-7B-Instruct-v0.2-stockname_103k-sft-lora is an advanced text generation AI model tailored by 2digit specifically for news analysis purposes. |
|
|
|
* **Company Name Extraction**: This model proficiently identifies and extracts the names of companies mentioned in news pieces. This functionality is invaluable for financial analysis, offering insights into market sentiment and potential stock movements by tracking company mentions in the media. |
|
|
|
**Advantages:** |
|
|
|
* **Sophistication**: Mistral-7B-Instruct-v0.2-stockname_103k-sft-lora boasts sophisticated algorithms, ensuring accurate extraction and analysis of company names from diverse news sources. |
|
* **Productive**: By automating the extraction process, Mistral-7B-Instruct-v0.2-stockname_103k-sft-lora saves valuable time for financial analysts, journalists, market researchers, and investors, enabling them to focus on analyzing extracted data and making informed decisions promptly. |
|
|
|
In summary, Mistral-7B-Instruct-v0.2-stockname_103k-sft-lora stands out as a potent asset for news analysis, facilitating quicker and more efficient decision-making processes by delivering crucial insights extracted from news articles. |
|
|
|
|
|
## License |
|
|
|
Use of this model requires company approval. Please contact AI@2digit.io. For more details, please refer to the website below: https://2digit.io/#contactus |
|
|
|
|
|
|
|
## Dataset |
|
|
|
The model was trained on an internal dataset from 2digit, consisting of 15k dataset. |
|
|
|
| size | description | |
|
|--------:|---------------------------------| |
|
| 103,643 | Human-labeled stockname dataset | |
|
|
|
|
|
|
|
## Evaluation |
|
|
|
We measured model accuracy through an internal evaluation system. |
|
|
|
| task | accuracy | description | |
|
|-----------|---------:|-------------------| |
|
| stockname | 0.90 | Extract companies | |
