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
```

Could not load Model

#28

by Ibrahim-Ola - opened Jun 8, 2023

Discussion

Ibrahim-Ola

Jun 8, 2023

I'm getting the following the error below when I try to load my model on Ubuntu and MacOS (i7, 2018)

ValueError: Could not load model tiiuae/falcon-7b-instruct with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'>,).

Note: all my packages are up to date. My pipeline is:

model = "tiiuae/falcon-7b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model)

pipeline = pipeline(
task="text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)

Any help is appreciated.

Thanks!

thewilltejeda

Jun 9, 2023

•

edited Jun 9, 2023

Same issue here

I'm on a 16" M1 Pro macbook 16GB RAM 16Core GPU ,

Python3.9.2


Traceback (most recent call last):
  File "/Users/__/Code/FalconLLM/./main.py", line 11, in <module>
    pipeline = transformers.pipeline(
               ^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/transformers/pipelines/__init__.py", line 788, in pipeline
    framework, model = infer_framework_load_model(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/transformers/pipelines/base.py", line 278, in infer_framework_load_model
    raise ValueError(f"Could not load model {model} with any of the following classes: {class_tuple}.")
ValueError: Could not load model tiiuae/falcon-7b with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'>,).

ihendley

Jun 9, 2023

I was able to load it and generate text on my 64GB M1 Max after upgrading torch to the latest 2.01 via pip install --upgrade torch and then changing torch_dtype=torch.bfloat16 to torch_dtype=torch.float32 in the pipeline. However the generation was extremely slow.

Ibrahim-Ola

Jun 9, 2023

I was able to load it and generate text on my 64GB M1 Max after upgrading torch to the latest 2.01 via pip install --upgrade torch and then changing torch_dtype=torch.bfloat16 to torch_dtype=torch.float32 in the pipeline. However the generation was extremely slow.

I changed torch_dtype=torch.bfloat16 to torch_dtype=torch.float32, but I still get the same error. My torch is the latest. I am on 16GB RAM, though.

therealcyberlord

Jun 12, 2023

having the same issue as well

prasantapanja

Jun 12, 2023

•

edited Jun 12, 2023

Facing same issue. Running on Mac M1. Can it be due to low memory as I'm using 8 GB RAM?

manuelrech

Jun 13, 2023

Same issue here, I was using it smoothly and suddenly it threw this error, no changes, no upgrades, downgrades.

nessian

Jun 15, 2023

I am on Mac M1 as well and same issue

Ibrahim-Ola

Jun 15, 2023

I'm getting the following the error below when I try to load my model on Ubuntu and MacOS (i7, 2018)

ValueError: Could not load model tiiuae/falcon-7b-instruct with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'>,).

Note: all my packages are up to date. My pipeline is:

model = "tiiuae/falcon-7b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model)

pipeline = pipeline(
task="text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)

Any help is appreciated.

Thanks!

I found a way to make it work:

from transformers import AutoModelForCausalLM

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

Ibrahim-Ola changed discussion status to closed Jun 15, 2023

vpkprasanna

Aug 10, 2023

I'm getting the following the error below when I try to load my model on Ubuntu and MacOS (i7, 2018)

ValueError: Could not load model tiiuae/falcon-7b-instruct with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'>,).

Note: all my packages are up to date. My pipeline is:

model = "tiiuae/falcon-7b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model)

pipeline = pipeline(
task="text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)

Any help is appreciated.

Thanks!
Even i got the same error but when i specify device manually as "cuda" in device_map parameter it starts to load the model . try this method once

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