Instructions to use BeastyZ/e5-R-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeastyZ/e5-R-mistral-7b with Transformers:

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

pipe = pipeline("text-generation", model="BeastyZ/e5-R-mistral-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BeastyZ/e5-R-mistral-7b")
model = AutoModelForCausalLM.from_pretrained("BeastyZ/e5-R-mistral-7b")

Inference
Local Apps Settings

vLLM

How to use BeastyZ/e5-R-mistral-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BeastyZ/e5-R-mistral-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BeastyZ/e5-R-mistral-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BeastyZ/e5-R-mistral-7b

SGLang

How to use BeastyZ/e5-R-mistral-7b 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 "BeastyZ/e5-R-mistral-7b" \
    --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": "BeastyZ/e5-R-mistral-7b",
		"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 "BeastyZ/e5-R-mistral-7b" \
        --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": "BeastyZ/e5-R-mistral-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BeastyZ/e5-R-mistral-7b with Docker Model Runner:
```
docker model run hf.co/BeastyZ/e5-R-mistral-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for e5-R-mistral-7b

Model Description

e5-R-mistral-7b is a LLM retriever fine-tuned from mistralai/Mistral-7B-v0.1.

Model type: CausalLM
Repository: Welcome to our GitHub repository to obtain code
Training dataset: Dataset used for fine-tuning e5-R-mistral-7b is available here.

Downloads last month: 150

Safetensors

Model size

7B params

Tensor type

F32

Model tree for BeastyZ/e5-R-mistral-7b

Quantizations

2 models

Dataset used to train BeastyZ/e5-R-mistral-7b

Spaces using BeastyZ/e5-R-mistral-7b 20

Evaluation results

map_at_1 on MTEB ArguAna
test set self-reported

33.570
map_at_10 on MTEB ArguAna
test set self-reported

49.952
map_at_100 on MTEB ArguAna
test set self-reported

50.673
map_at_1000 on MTEB ArguAna
test set self-reported

50.674
map_at_3 on MTEB ArguAna
test set self-reported

44.915
map_at_5 on MTEB ArguAna
test set self-reported

47.877
mrr_at_1 on MTEB ArguAna
test set self-reported

34.211
mrr_at_10 on MTEB ArguAna
test set self-reported

50.190