Instructions to use OpenNLPLab/TransNormerLLM-385M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenNLPLab/TransNormerLLM-385M with Transformers:

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

pipe = pipeline("text-generation", model="OpenNLPLab/TransNormerLLM-385M", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-385M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenNLPLab/TransNormerLLM-385M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenNLPLab/TransNormerLLM-385M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenNLPLab/TransNormerLLM-385M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenNLPLab/TransNormerLLM-385M

SGLang

How to use OpenNLPLab/TransNormerLLM-385M 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 "OpenNLPLab/TransNormerLLM-385M" \
    --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": "OpenNLPLab/TransNormerLLM-385M",
		"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 "OpenNLPLab/TransNormerLLM-385M" \
        --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": "OpenNLPLab/TransNormerLLM-385M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenNLPLab/TransNormerLLM-385M with Docker Model Runner:
```
docker model run hf.co/OpenNLPLab/TransNormerLLM-385M
```

OpenNLPLab commited on Oct 15, 2023

Commit

fc689fe

1 Parent(s): 8d3a720

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -144,8 +144,8 @@ export use_triton=False
 ```python
 >>> from transformers import AutoModelForCausalLM, AutoTokenizer
->>> tokenizer = AutoTokenizer.from_pretrained("OpenNLPLab/TransNormerLLM-1B", trust_remote_code=True)
->>> model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-1B", device_map="auto", trust_remote_code=True)
 >>> inputs = tokenizer('今天是美好的一天', return_tensors='pt')
 >>> pred = model.generate(**inputs, max_new_tokens=2048, repetition_penalty=1.0)
 >>> print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
@@ -175,7 +175,7 @@ Training Data: `alpaca_data.json`. This sample data was drawn from [alpaca_data.
 torchrun \
     --nproc_per_node=8 \
     train.py \
-    --model_name_or_path OpenNLPLab/TransNormerLLM-1B \
     --data_path ./alpaca_data.json \
     --output_dir output \
     --num_train_epochs 1 \

 ```python
 >>> from transformers import AutoModelForCausalLM, AutoTokenizer
+>>> tokenizer = AutoTokenizer.from_pretrained("OpenNLPLab/TransNormerLLM-385M", trust_remote_code=True)
+>>> model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-385M", device_map="auto", trust_remote_code=True)
 >>> inputs = tokenizer('今天是美好的一天', return_tensors='pt')
 >>> pred = model.generate(**inputs, max_new_tokens=2048, repetition_penalty=1.0)
 >>> print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
 torchrun \
     --nproc_per_node=8 \
     train.py \
+    --model_name_or_path OpenNLPLab/TransNormerLLM-385M \
     --data_path ./alpaca_data.json \
     --output_dir output \
     --num_train_epochs 1 \