Instructions to use CohereLabs/c4ai-command-r-plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/c4ai-command-r-plus with Transformers:

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

pipe = pipeline("text-generation", model="CohereLabs/c4ai-command-r-plus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-r-plus")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/c4ai-command-r-plus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CohereLabs/c4ai-command-r-plus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/c4ai-command-r-plus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CohereLabs/c4ai-command-r-plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/c4ai-command-r-plus

SGLang

How to use CohereLabs/c4ai-command-r-plus 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 "CohereLabs/c4ai-command-r-plus" \
    --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": "CohereLabs/c4ai-command-r-plus",
		"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 "CohereLabs/c4ai-command-r-plus" \
        --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": "CohereLabs/c4ai-command-r-plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/c4ai-command-r-plus with Docker Model Runner:
```
docker model run hf.co/CohereLabs/c4ai-command-r-plus
```

Is the hugginface implementation broken?

#21

by useless-ai - opened Apr 9, 2024

Discussion

useless-ai

Apr 9, 2024

I can't get anything but some gibberish out of this model using the sample code, has anyone managed to make it work?

example:
<|START_OF_TURN_TOKEN|><|USER_TOKEN|>write a python script to send an http request<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>-sectionauthor
sectionauthor
sectionauthor
sectionauthor-sectionauthor-sectionauthor-sectionauthor
sectionauthor
sectionauthor
sectionauthor
sectionauthor
sectionauthor-sectionauthor-sectionauthor
begin-sectionauthor-sectionauthor-section-sectionauthor-sectionauthor-sectionauthor-sectionauthor
author
begin-begin-begin-begin-begin-begin-begin-begin-sectionauthor-begin-begin
author-begin-begin-begin-author-begin-begin-begin-author-begin-begin-author-author-author-author-author-author-author-author-begin-author-begin-author-author-author-author-author-author-author-author-author-begin-author-author-author-author-author-author-author-author-author-author-n-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author-author--author-author--author---author--author--author-author-----author--author--------------

mthreet

Apr 9, 2024

I'm getting a similar response using HuggingFace TGI with this model as well.

coherecode

Cohere Labs org Apr 9, 2024

hi, this might be due to your transformers version. For this model, you should install transformers from the source repo (latest commit) using pip install 'git+https://github.com/huggingface/transformers.git' as it includes modifications required for this model.

useless-ai

Apr 10, 2024

Thanks that was the problem

useless-ai changed discussion status to closed Apr 10, 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