Instructions to use Sefika/mistral_fewrel_10_7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sefika/mistral_fewrel_10_7 with Transformers:

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

pipe = pipeline("text-generation", model="Sefika/mistral_fewrel_10_7")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sefika/mistral_fewrel_10_7")
model = AutoModelForCausalLM.from_pretrained("Sefika/mistral_fewrel_10_7")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Sefika/mistral_fewrel_10_7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sefika/mistral_fewrel_10_7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sefika/mistral_fewrel_10_7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sefika/mistral_fewrel_10_7

SGLang

How to use Sefika/mistral_fewrel_10_7 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 "Sefika/mistral_fewrel_10_7" \
    --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": "Sefika/mistral_fewrel_10_7",
		"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 "Sefika/mistral_fewrel_10_7" \
        --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": "Sefika/mistral_fewrel_10_7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sefika/mistral_fewrel_10_7 with Docker Model Runner:
```
docker model run hf.co/Sefika/mistral_fewrel_10_7
```

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Sefika
Language(s) (NLP): EN
License: MIT
Finetuned from model [optional]: mistralai/Mistral-7B-Instruct-v0.2

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Direct Use

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

tokenizer = "mistralai/Mistral-7B-Instruct-v0.2"
model_id = "Sefika/mistral_fewrel_10_7"
tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    load_in_4bit=True,  # Requires bitsandbytes
    torch_dtype="auto"
)

Testing Data

FewRel

BibTeX: The paper "Large Language Models for Continual Relation Extraction" is submitted to Springer Machine Learning journal

Model Card Contact

sefika efeoglu

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

F32

F16

Collection including Sefika/mistral_fewrel_10_7

LLMs for CRE

Collection

The models trained with Llama, and Mistral on FewRel dataset. The paper of the work has been submitted to possible journal • 20 items • Updated Aug 23, 2025