Instructions to use zai-org/cogvlm2-llama3-chat-19B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/cogvlm2-llama3-chat-19B with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/cogvlm2-llama3-chat-19B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("zai-org/cogvlm2-llama3-chat-19B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/cogvlm2-llama3-chat-19B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/cogvlm2-llama3-chat-19B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/cogvlm2-llama3-chat-19B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/cogvlm2-llama3-chat-19B

SGLang

How to use zai-org/cogvlm2-llama3-chat-19B 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 "zai-org/cogvlm2-llama3-chat-19B" \
    --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": "zai-org/cogvlm2-llama3-chat-19B",
		"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 "zai-org/cogvlm2-llama3-chat-19B" \
        --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": "zai-org/cogvlm2-llama3-chat-19B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/cogvlm2-llama3-chat-19B with Docker Model Runner:
```
docker model run hf.co/zai-org/cogvlm2-llama3-chat-19B
```

Update of modeling_cogvlm.py for Transformers newer version

#15

by Qishuai - opened Aug 15, 2024

base: refs/heads/main

←

from: refs/pr/15

Discussion Files changed

+15

-4

Qishuai

Aug 15, 2024

•

edited Aug 20, 2024

Compatible with Transformers > 4.41.2

Details:

The current implementation has an error with the line:

if past_key_values is not None:
            past_key_values_length = past_key_values[0][0].shape[2]
            seq_length_with_past = seq_length_with_past + past_key_values_length

When the Transformers version is > 4.41.2.
The issue is caused by the change in the output of
_extract_past_from_model_output function defined in Transformers src/transformers/generation/utils.py since version v4.42.0. I tested that this fix works with transformers 4.44.0 as well.

Therefore, my pr includes checking the version of Transformers and modifying the process of the output of _extract_past_from_model_output to make sure cogvlm2 can work with both the newer version of Transformers, e.g., 4.44.0 and the version below 4.42.0

Upload modeling_cogvlm.pye3c7deb0

Qishuai changed pull request title from Upload modeling_cogvlm.py to Update of modeling_cogvlm.py for Transformers newer version Aug 15, 2024

Lester16

Aug 20, 2024

This solved my issue!

ZHANGYUXUAN-zR

Z.ai org Aug 20, 2024

cogvlm-videos have changed to support transformers 4.44.0, I will copy from that changed asap

Qishuai

Aug 20, 2024

•

edited Aug 20, 2024

This pr works for transformer 4.44.0 as well. I think it can be an option to just merge this pr 😃

Qishuai

Aug 26, 2024

hi can you test and merge this pr?

ZHANGYUXUAN-zR changed pull request status to merged Aug 26, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment