Instructions to use CogwiseAI/CogwiseAI-chatwithMS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CogwiseAI/CogwiseAI-chatwithMS with Transformers:

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

pipe = pipeline("text-generation", model="CogwiseAI/CogwiseAI-chatwithMS", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CogwiseAI/CogwiseAI-chatwithMS", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CogwiseAI/CogwiseAI-chatwithMS with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CogwiseAI/CogwiseAI-chatwithMS

SGLang

How to use CogwiseAI/CogwiseAI-chatwithMS 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 "CogwiseAI/CogwiseAI-chatwithMS" \
    --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": "CogwiseAI/CogwiseAI-chatwithMS",
		"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 "CogwiseAI/CogwiseAI-chatwithMS" \
        --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": "CogwiseAI/CogwiseAI-chatwithMS",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CogwiseAI/CogwiseAI-chatwithMS with Docker Model Runner:
```
docker model run hf.co/CogwiseAI/CogwiseAI-chatwithMS
```

CogwiseAI commited on Jul 4, 2023

Commit

a3a3f1f

1 Parent(s): df9603e

Update app.py

Browse files

Files changed (1) hide show

app.py +3 -2

app.py CHANGED Viewed

@@ -217,7 +217,8 @@ def handle_input():
     # prompt = "Debate the merits and demerits of introducing simultaneous elections in India?"
     prompt=input
-    answer=print(generate_response(prompt))
     # answer='Yes'
     chat_history.append((input, answer))
@@ -254,4 +255,4 @@ with st.container():
         write_chat_message(a, q)
 st.markdown('---')
-input = st.text_input("You are talking to an AI, ask any question.", key="input", on_change=handle_input)

     # prompt = "Debate the merits and demerits of introducing simultaneous elections in India?"
     prompt=input
+    answer=generate_response(prompt)
+    print(answer)
     # answer='Yes'
     chat_history.append((input, answer))
         write_chat_message(a, q)
 st.markdown('---')
+input = st.text_input("You are talking to an AI, ask any question.", key="input", on_change=handle_input)