Instructions to use NousResearch/Genstruct-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Genstruct-7B with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Genstruct-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Genstruct-7B")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Genstruct-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NousResearch/Genstruct-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NousResearch/Genstruct-7B

SGLang

How to use NousResearch/Genstruct-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 "NousResearch/Genstruct-7B" \
    --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": "NousResearch/Genstruct-7B",
		"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 "NousResearch/Genstruct-7B" \
        --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": "NousResearch/Genstruct-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NousResearch/Genstruct-7B with Docker Model Runner:
```
docker model run hf.co/NousResearch/Genstruct-7B
```

Dataset?

by Nekochu - opened Mar 8, 2024

Discussion

Nekochu

Mar 8, 2024

what dataset was it train? is openly available?

medmac01

Mar 10, 2024

Apparently (not so sure but based on the paper) they finetuned based on ada-instruct, they have a dataset on their repo.

Check this
https://github.com/wangitu/Ada-Instruct/tree/main/data%2Fada-instruct

euclaise

Mar 10, 2024

•

edited Mar 10, 2024

We did not use the Ada-instruct dataset

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

euclaise changed discussion status to closed Mar 10, 2024

Nekochu

Mar 10, 2024

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

Looking forward to being shared.

Kalamazooter

Mar 12, 2024

We did not use the Ada-instruct dataset

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

was the dataset really that small? @euclaise , kind of suprising considering the size of some STF datasets these days.

euclaise

Mar 12, 2024

•

edited Mar 12, 2024

We did not use the Ada-instruct dataset

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

was the dataset really that small? @euclaise , kind of suprising considering the size of some STF datasets these days.

Yes. The original Ada-instruct even used only 10 examples

I trained for dozens of epochs though

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