Instructions to use CohereLabs/c4ai-command-r7b-12-2024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/c4ai-command-r7b-12-2024 with Transformers:

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

pipe = pipeline("text-generation", model="CohereLabs/c4ai-command-r7b-12-2024")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-r7b-12-2024")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/c4ai-command-r7b-12-2024", device_map="auto")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CohereLabs/c4ai-command-r7b-12-2024 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/c4ai-command-r7b-12-2024"
# 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-r7b-12-2024",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/c4ai-command-r7b-12-2024

SGLang

How to use CohereLabs/c4ai-command-r7b-12-2024 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-r7b-12-2024" \
    --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-r7b-12-2024",
		"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-r7b-12-2024" \
        --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-r7b-12-2024",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/c4ai-command-r7b-12-2024 with Docker Model Runner:
```
docker model run hf.co/CohereLabs/c4ai-command-r7b-12-2024
```

Opportunities `is_error` flag

#13

by DiTy - opened Jan 22, 2025

Discussion

DiTy

Jan 22, 2025

•

edited Jan 22, 2025

Hey,
I noticed when I use tool role in the conversation is_error appears in the prompt. At the same time this attribute always is null in jinja chat template code.
Do you have any advices how can I use it?

<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
    {
        "tool_call_id": "0",
        "results": {
            "0": {"date": "2023-09-29", "summary": "Total Sales Amount: 10000, Total Units Sold: 250"}
        },
        "is_error": null
    }
]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>

P.S. I have checked your tool use documentation and I have found nothing about that

maximevoisin1212

Feb 9, 2025

Hi @DiTy , correct, we add this under the hood in the prompt. The model was trained with this attribute, so we inject it in the prompt.

Do you have any advices how can I use it?

Best thing to do, is to not worry about it: "is_error": null show up automatically when you build the prompts. Leave it there as :)

DiTy changed discussion status to closed Feb 9, 2025

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