Instructions to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with Transformers:

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

pipe = pipeline("text-generation", model="OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints

SGLang

How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints 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/TransNormerLLM3-15B-Intermediate-Checkpoints" \
    --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/TransNormerLLM3-15B-Intermediate-Checkpoints",
		"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/TransNormerLLM3-15B-Intermediate-Checkpoints" \
        --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/TransNormerLLM3-15B-Intermediate-Checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with Docker Model Runner:
```
docker model run hf.co/OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints
```

OpenNLPLab commited on Jan 10, 2024

Commit

b682e49

1 Parent(s): 8b00bb1

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -25,8 +25,6 @@ This official repository unveils the TransNormerLLM3 model along with its open-s
 - **TransNormerLLM3-15B** features **14.83 billion** parameters. It is structured with **42 layers**, includes **40 attention heads**, and has a total **embedding size of 5120**.
 - **TransNormerLLM3-15B** is purely intergrated with **[Lightning Attention-2](http://arxiv.org/abs/2401.04658)**, which can maintain a **stable TGS** during training of **unlimited sequence lengths**, up until encountering firm limitations like GPU memory constraints.
 - **Titoken** tokenizer is used with a total **vocabulary size** of about **100,000**.
-- It incorporates **Simple GLU** for its channel mixer, **GLA** in the token mixer, and **SRMSNorm** for normalization.
-- In terms of position encoding, the first layer employs **LRPE with exponential decay**, whereas the subsequent layers continue with **exponential decay encoding**.
 ### Pre-training Logbook
 * Realtime Track: https://api.wandb.ai/links/opennlplab/kip314lq

 - **TransNormerLLM3-15B** features **14.83 billion** parameters. It is structured with **42 layers**, includes **40 attention heads**, and has a total **embedding size of 5120**.
 - **TransNormerLLM3-15B** is purely intergrated with **[Lightning Attention-2](http://arxiv.org/abs/2401.04658)**, which can maintain a **stable TGS** during training of **unlimited sequence lengths**, up until encountering firm limitations like GPU memory constraints.
 - **Titoken** tokenizer is used with a total **vocabulary size** of about **100,000**.
 ### Pre-training Logbook
 * Realtime Track: https://api.wandb.ai/links/opennlplab/kip314lq