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

Libraries

How to use Open-Orca/Mistral-7B-SlimOrca with Transformers:

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

pipe = pipeline("text-generation", model="Open-Orca/Mistral-7B-SlimOrca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Open-Orca/Mistral-7B-SlimOrca")
model = AutoModelForCausalLM.from_pretrained("Open-Orca/Mistral-7B-SlimOrca")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Open-Orca/Mistral-7B-SlimOrca with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Open-Orca/Mistral-7B-SlimOrca

SGLang

How to use Open-Orca/Mistral-7B-SlimOrca 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 "Open-Orca/Mistral-7B-SlimOrca" \
    --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": "Open-Orca/Mistral-7B-SlimOrca",
		"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 "Open-Orca/Mistral-7B-SlimOrca" \
        --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": "Open-Orca/Mistral-7B-SlimOrca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Open-Orca/Mistral-7B-SlimOrca with Docker Model Runner:
```
docker model run hf.co/Open-Orca/Mistral-7B-SlimOrca
```

finetuning parameters

by lvkaokao - opened Oct 16, 2023

Discussion

lvkaokao

Oct 16, 2023

hi, can you share the finetuning hyper-parameters?

I have finetuned the https://huggingface.co/mistralai/Mistral-7B-v0.1 with your dataset, but the metric of ARC and hellaswag decreases significantly during the training

here are some information of my hyper-parameters

full parameters finetuning
learning rate = 5e-6
batch_size=64
epoch=3

xDAN2099

OpenOrca org Oct 16, 2023

The batch_size is too huge and you should set to 4 or 6 is better.
I would prefer set the learning rate as 2e-5

lvkaokao

Oct 16, 2023

Thanks for your response~
I will try!

lvkaokao

Oct 16, 2023

@xDAN2099
hi, what about other parameters?

I set
full parameters finetuning
learning rate = 2e-5
batch_size=8
epoch=3
warmup_ratio = 0.03

but the training loss don't coverage

timlim123

Dec 5, 2023

@lvkaokao how did u fine-tune? was it using axolotl too?

Vidh

Feb 2, 2024

@xDAN2099 and others, I'm trying to finetune Mistral 7B with SlimOrca and the MT-bench score is consistently well-below the OpenOrca benchmarked 6.84. Could you please share the exact training script along with any other details on hardware used to get on-par score on MT-bench? Any help in that regard is much appreciated, thank you!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment