Instructions to use neukg/TechGPT-2.0-atom-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neukg/TechGPT-2.0-atom-hf with Transformers:

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

pipe = pipeline("text-generation", model="neukg/TechGPT-2.0-atom-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neukg/TechGPT-2.0-atom-hf")
model = AutoModelForCausalLM.from_pretrained("neukg/TechGPT-2.0-atom-hf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use neukg/TechGPT-2.0-atom-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neukg/TechGPT-2.0-atom-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neukg/TechGPT-2.0-atom-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/neukg/TechGPT-2.0-atom-hf

SGLang

How to use neukg/TechGPT-2.0-atom-hf 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 "neukg/TechGPT-2.0-atom-hf" \
    --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": "neukg/TechGPT-2.0-atom-hf",
		"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 "neukg/TechGPT-2.0-atom-hf" \
        --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": "neukg/TechGPT-2.0-atom-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use neukg/TechGPT-2.0-atom-hf with Docker Model Runner:
```
docker model run hf.co/neukg/TechGPT-2.0-atom-hf
```

Add LICENSE

by davanstrien HF Staff - opened Jan 10, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-2

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -1,3 +1,6 @@
 # TechGPT 2.0: Technology-Oriented Generative Pretrained Transformer 2.0
 Demo: [TechGPT-neukg](http://techgpt.neukg.com) <br>
 HuggingFace🤗: [neukg/TechGPT-7B](https://huggingface.co/neukg)
@@ -460,5 +463,4 @@ TechGPT-2.0 在保留了 TechGPT-1.0 模型的通用能力、实体识别能力
     url={https://arxiv.org/abs/2304.08177},
     year={2023}
 }
-```

+---
+license: apache-2.0
+---
 # TechGPT 2.0: Technology-Oriented Generative Pretrained Transformer 2.0
 Demo: [TechGPT-neukg](http://techgpt.neukg.com) <br>
 HuggingFace🤗: [neukg/TechGPT-7B](https://huggingface.co/neukg)
     url={https://arxiv.org/abs/2304.08177},
     year={2023}
 }
+```