Instructions to use NaughtyDog97/DFE-GPS-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NaughtyDog97/DFE-GPS-34B with Transformers:

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

pipe = pipeline("text-generation", model="NaughtyDog97/DFE-GPS-34B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NaughtyDog97/DFE-GPS-34B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NaughtyDog97/DFE-GPS-34B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NaughtyDog97/DFE-GPS-34B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NaughtyDog97/DFE-GPS-34B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NaughtyDog97/DFE-GPS-34B

SGLang

How to use NaughtyDog97/DFE-GPS-34B 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 "NaughtyDog97/DFE-GPS-34B" \
    --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": "NaughtyDog97/DFE-GPS-34B",
		"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 "NaughtyDog97/DFE-GPS-34B" \
        --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": "NaughtyDog97/DFE-GPS-34B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NaughtyDog97/DFE-GPS-34B with Docker Model Runner:
```
docker model run hf.co/NaughtyDog97/DFE-GPS-34B
```

zezeze97 commited on Jul 28, 2024

Commit

5f96533

1 Parent(s): 27df1a3

111

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -36,7 +36,9 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(
     'NaughtyDog97/FormalEnhencedGPS-34B',
-    trust_remote_code=True)
 # text prompt
 img_path = 'sample/4927.png'
@@ -140,6 +142,8 @@ formalization_model = AutoModelForCausalLM.from_pretrained(
 formalization_tokenizer = AutoTokenizer.from_pretrained(
     'NaughtyDog97/GeoFormalizer',
     trust_remote_code=True)
@@ -150,6 +154,7 @@ reason_model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True)
 reason_tokenizer = AutoTokenizer.from_pretrained(
     'NaughtyDog97/FormalEnhencedGPS-34B',
     trust_remote_code=True)

     trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(
     'NaughtyDog97/FormalEnhencedGPS-34B',
+    use_fast=False,
+    trust_remote_code=True,
+)
 # text prompt
 img_path = 'sample/4927.png'
 formalization_tokenizer = AutoTokenizer.from_pretrained(
     'NaughtyDog97/GeoFormalizer',
+    use_fast=True,
+    padding_side="right",
     trust_remote_code=True)
     trust_remote_code=True)
 reason_tokenizer = AutoTokenizer.from_pretrained(
     'NaughtyDog97/FormalEnhencedGPS-34B',
+    use_fast=False,
     trust_remote_code=True)