Instructions to use akjindal53244/Mistral-7B-v0.1-Open-Platypus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akjindal53244/Mistral-7B-v0.1-Open-Platypus with Transformers:

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

pipe = pipeline("text-generation", model="akjindal53244/Mistral-7B-v0.1-Open-Platypus")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("akjindal53244/Mistral-7B-v0.1-Open-Platypus")
model = AutoModelForCausalLM.from_pretrained("akjindal53244/Mistral-7B-v0.1-Open-Platypus", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use akjindal53244/Mistral-7B-v0.1-Open-Platypus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akjindal53244/Mistral-7B-v0.1-Open-Platypus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akjindal53244/Mistral-7B-v0.1-Open-Platypus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/akjindal53244/Mistral-7B-v0.1-Open-Platypus

SGLang

How to use akjindal53244/Mistral-7B-v0.1-Open-Platypus 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 "akjindal53244/Mistral-7B-v0.1-Open-Platypus" \
    --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": "akjindal53244/Mistral-7B-v0.1-Open-Platypus",
		"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 "akjindal53244/Mistral-7B-v0.1-Open-Platypus" \
        --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": "akjindal53244/Mistral-7B-v0.1-Open-Platypus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use akjindal53244/Mistral-7B-v0.1-Open-Platypus with Docker Model Runner:
```
docker model run hf.co/akjindal53244/Mistral-7B-v0.1-Open-Platypus
```

Model is instruction-finetuned using Open-Platypus dataset: https://huggingface.co/datasets/garage-bAInd/Open-Platypus

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	53.64
ARC (25-shot)	62.37
HellaSwag (10-shot)	85.08
MMLU (5-shot)	63.79
TruthfulQA (0-shot)	47.33
Winogrande (5-shot)	77.66
GSM8K (5-shot)	17.29
DROP (3-shot)	21.93

Support My Work

Building LLMs takes time and resources; if you find my work interesting, your support would be epic!

Downloads last month: 49

Model tree for akjindal53244/Mistral-7B-v0.1-Open-Platypus

Merges

5 models

akjindal53244
/

Mistral-7B-v0.1-Open-Platypus

Open LLM Leaderboard Evaluation Results

Support My Work

Model tree for akjindal53244/Mistral-7B-v0.1-Open-Platypus

Spaces using akjindal53244/Mistral-7B-v0.1-Open-Platypus 9