Instructions to use tiiuae/falcon-mamba-7b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/falcon-mamba-7b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/falcon-mamba-7b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b-instruct", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiiuae/falcon-mamba-7b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/falcon-mamba-7b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/falcon-mamba-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/falcon-mamba-7b-instruct

SGLang

How to use tiiuae/falcon-mamba-7b-instruct 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 "tiiuae/falcon-mamba-7b-instruct" \
    --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": "tiiuae/falcon-mamba-7b-instruct",
		"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 "tiiuae/falcon-mamba-7b-instruct" \
        --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": "tiiuae/falcon-mamba-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiiuae/falcon-mamba-7b-instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/falcon-mamba-7b-instruct
```

Sometimes I've empty answer

#13

by Yarflam - opened Aug 30, 2024

Discussion

Yarflam

Aug 30, 2024

The model replies in general, but sometimes nothing is generate.

I started my talk with a basic preprompt without any problem:

And 6 messages later:

I don't see any error in my runpod instance:

I've the impression that this happens more frequently when the end doesn't finish with punctuation (to be verified, of course).

The model is running with minimum parameters:

outputs = self.model.generate(
    encodeds.to(self.device),
    num_return_sequences=options['n'],
    max_new_tokens=options['max_new_tokens'],
    do_sample=options['do_sample'],
    temperature=options['temperature'],
    top_p=options['top_p'],
    pad_token_id=self.tokenizer.eos_token_id
)

If you have any idea about the reasons or debug approach to determine the bug.

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