Instructions to use sunzeyeah/pangu-350M-reward with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sunzeyeah/pangu-350M-reward with Transformers:

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

pipe = pipeline("text-generation", model="sunzeyeah/pangu-350M-reward", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("sunzeyeah/pangu-350M-reward", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sunzeyeah/pangu-350M-reward with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunzeyeah/pangu-350M-reward"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunzeyeah/pangu-350M-reward",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sunzeyeah/pangu-350M-reward

SGLang

How to use sunzeyeah/pangu-350M-reward 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 "sunzeyeah/pangu-350M-reward" \
    --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": "sunzeyeah/pangu-350M-reward",
		"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 "sunzeyeah/pangu-350M-reward" \
        --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": "sunzeyeah/pangu-350M-reward",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sunzeyeah/pangu-350M-reward with Docker Model Runner:
```
docker model run hf.co/sunzeyeah/pangu-350M-reward
```

sunzeyeah commited on Apr 6, 2023

Commit

697cbb6

1 Parent(s): 38daab8

update modeling

Browse files

Files changed (1) hide show

modeling_gptpangu.py +1 -1

modeling_gptpangu.py CHANGED Viewed

@@ -460,7 +460,7 @@ class GPTPanguForCausalLM(GPTPanguPreTrainedModel):
         if attention_mask is not None and position_ids is None:
             # create position_ids on the fly for batch generation
-            position_ids = attention_mask.long().cumsum(-1) - 1
             position_ids.masked_fill_(attention_mask == 0, 1)
             if past:
                 position_ids = position_ids[:, -1].unsqueeze(-1)

         if attention_mask is not None and position_ids is None:
             # create position_ids on the fly for batch generation
+            position_ids = attention_mask.int().cumsum(-1).long() - 1
             position_ids.masked_fill_(attention_mask == 0, 1)
             if past:
                 position_ids = position_ids[:, -1].unsqueeze(-1)