Instructions to use davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora

SGLang

How to use davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora 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 "davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora with Docker Model Runner:
```
docker model run hf.co/davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora
```

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Mistral-7B-Instruct-v0.2-category_24k-sft-lora

Model Details

Mistral-7B-Instruct-v0.2-category_24k-sft-lora is an advanced text generation AI model created by 2digit specifically tailored for news analysis purposes.

Category Identification: Mistral-7B-Instruct-v0.2-category_24k-sft-lora excels in categorizing news articles into predefined categories. This feature aids in efficiently organizing news content, facilitating easy access to articles relevant to specific topics of interest. The labeled category list includes: publicity, incidents, key figures within companies, market trends, contracts, social activities, collaborations, business ventures, events, opinions, disclosures, bonds, and interest rates.

Advantages:

Efficiency: It automates the categorization process, saving time and effort for users involved in news analysis.
Precision: Its sophisticated algorithms ensure accurate categorization, reducing the likelihood of misclassification and providing reliable results.
Versatility: Suitable for a wide range of professionals, including financial analysts, journalists, market researchers, and investors, it adapts to various needs within the realm of news analysis.

Mistral-7B-Instruct-v0.2-category_24k-sft-lora emerges as a robust solution for enhancing the efficiency and accuracy of news analysis processes, catering to the diverse needs of professionals across different industries.

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
24,605	Human labeling of 13 categories

Evaluation

We measured model accuracy through an internal evaluation system.

task	accuracy	description
category	0.92	News category classification

Downloads last month: -; Downloads are not tracked for this model. How to track

Collection including davidkim205/Mistral-7B-Instruct-v0.2-category_24k-sft-lora

2digit models

Collection

These are models specifically designed for financial use used by 2digit. These models can only be used after approval from the 2digit company. • 8 items • Updated Mar 2