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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-7b-instruct", trust_remote_code=True)
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

vLLM

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

Use Docker

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

SGLang

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

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

[Need Help] Would this model work if the input to this model is padded?

#27

by vivek0797 - opened Jun 8, 2023

Discussion

vivek0797

Jun 8, 2023

Hi, I'm trying to run this model with the set of padded inputs. I have set the following values:

tokenizer.padding_side = "left"
tokenizer.pad_token_id = 11

Along with the padded set of inputs, I'm not getting the correct results or the same as the non-padded input. Is this expected? Is this model expected to not work with the padded inputs?

After setting the random seed value to 0. I'm getting the following results:

Non-padded Input:

Result: Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Girafatron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.
Daniel: Hello, Girafatron!
Girafatron: Good morning, Daniel! How may I help you today?
Daniel: I need your help, Girafatron! How are you doing today?
Girafatron: Girafatron is doing fine! I'm just sitting around, enjoying my giraffe life.
Daniel: That sounds like a peaceful life! How long have you been living in the jungle, Girafatron?
Girafatron: I've been living here since the beginning of time, Daniel! It's a wonderful life in the jungle, with all these beautiful animals!
Daniel: Yeah, it's awesome! I wish I lived in the jungle too!
Girafatron: I'd love to visit the jungle one day, Daniel! Maybe you could come visit and join me for a giraffe safari?
Daniel: That would be amazing! I love giraffes, Girafatron, and I would love to join you for

Padded Input:

Result: Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Girafatron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.
Daniel: Hello, Girafatron!
Girafatron: You've got the right name.

vivek0797 changed discussion title from Would this model work if the input to this model is padded? to [Need Help] Would this model work if the input to this model is padded? Jun 8, 2023

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