Instructions to use Geksaida/llama-2-7b-SysML_test3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Geksaida/llama-2-7b-SysML_test3 with Transformers:

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

pipe = pipeline("text-generation", model="Geksaida/llama-2-7b-SysML_test3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Geksaida/llama-2-7b-SysML_test3")
model = AutoModelForCausalLM.from_pretrained("Geksaida/llama-2-7b-SysML_test3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Geksaida/llama-2-7b-SysML_test3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Geksaida/llama-2-7b-SysML_test3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Geksaida/llama-2-7b-SysML_test3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Geksaida/llama-2-7b-SysML_test3

SGLang

How to use Geksaida/llama-2-7b-SysML_test3 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 "Geksaida/llama-2-7b-SysML_test3" \
    --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": "Geksaida/llama-2-7b-SysML_test3",
		"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 "Geksaida/llama-2-7b-SysML_test3" \
        --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": "Geksaida/llama-2-7b-SysML_test3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Geksaida/llama-2-7b-SysML_test3 with Docker Model Runner:
```
docker model run hf.co/Geksaida/llama-2-7b-SysML_test3
```

how to use?

by Krusty84 - opened Apr 20, 2024

Discussion

Krusty84

Apr 20, 2024

Hello,
Can you provide some prompts example for playing with your model?
Thank you!

Geksaida

Owner Apr 20, 2024

Prompt should look like this:
[INST] You have to create a model in SysMLv2 language. /* system or model description here */ [/INST]

It has a poor quality and I'm workng on a new dataset to obtain much cleaner model. For now I have GPT that can create models that reqire only a bit of fixing.

Geksaida

Owner Apr 20, 2024

Here's a GPT
https://chat.openai.com/g/g-f0PS3JDdO-sysml-v2-systems-modeler

leiyl

Jun 9, 2025

Very good work. I would like to continue to follow up on your work and would like to ask if you can make the dataset public.

Geksaida

Owner Jun 9, 2025

Very good work. I would like to continue to follow up on your work and would like to ask if you can make the dataset public.

Sorry, but I've decided to go commercial and won't share the dataset as it requires a lot of skilled work.

leiyl

Jun 10, 2025

Sure. I'm a current master's student. I'm only doing this for academic research and am currently building a dataset. I have over a hundred data points built so far and am gradually improving the effect.I'm reaching out to you for any advice you might have. I look forward to learning and cooperating with you in the future.

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