Instructions to use Mathoctopus/Parallel_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mathoctopus/Parallel_7B with Transformers:

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

pipe = pipeline("text-generation", model="Mathoctopus/Parallel_7B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mathoctopus/Parallel_7B")
model = AutoModelForCausalLM.from_pretrained("Mathoctopus/Parallel_7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mathoctopus/Parallel_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mathoctopus/Parallel_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mathoctopus/Parallel_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mathoctopus/Parallel_7B

SGLang

How to use Mathoctopus/Parallel_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 "Mathoctopus/Parallel_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": "Mathoctopus/Parallel_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 "Mathoctopus/Parallel_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": "Mathoctopus/Parallel_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mathoctopus/Parallel_7B with Docker Model Runner:
```
docker model run hf.co/Mathoctopus/Parallel_7B
```

Parallel_7B

Commit History

Jan 10, 2025

04:09
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
9cacc40

Nov 2, 2023

07:29
Update README.md

compasszzn

fd84a03

Oct 22, 2023

02:12
Update README.md

compasszzn

fc7cda7

Oct 21, 2023

13:36
Update README.md

compasszzn

8397a1b

Oct 19, 2023

15:52
Update README.md

compasszzn

fa1230c

Oct 18, 2023

12:07
Update README.md

compasszzn

0f79b55
08:38
Update README.md

compasszzn

e59e9df
07:07
Update README.md

Nuo97

20d692d

Oct 16, 2023

12:25
Update README.md

Nuo97

36f8016
12:00
Update README.md

Nuo97

9e07b26

Oct 14, 2023

07:32
Update config.json

Nuo97

a0a1d18

Oct 13, 2023

15:10
Update README.md

Nuo97

d4c2be8
14:49
first_commit

nuochenpku

8811872
13:27
initial commit

Nuo97

80c6289

Commit History

Jan 10, 2025

Adding `safetensors` variant of this model⁠

Nov 2, 2023

Update README.md

Oct 22, 2023

Update README.md

Oct 21, 2023

Update README.md

Oct 19, 2023

Update README.md

Oct 18, 2023

Update README.md

Update README.md

Update README.md

Oct 16, 2023

Update README.md

Update README.md

Oct 14, 2023

Update config.json

Oct 13, 2023

Update README.md

first_commit

initial commit