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
```

No package metadata was found for bitsandbytes

#109

by Fyutong - opened Nov 20, 2023

Discussion

Fyutong

Nov 20, 2023

I try to run falcon-7b on local

pip install -q -U bitsandbytes
import torch
from transformers import BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
)

Traceback (most recent call last):
File "...", line 4, in
quantization_config = BitsAndBytesConfig(
File "...\Programs\Python\Python310\lib\site-packages\transformers\utils\quantization_config.py", line 212, in init
self.post_init()
File "...\Programs\Python\Python310\lib\site-packages\transformers\utils\quantization_config.py", line 238, in post_init
if self.load_in_4bit and not version.parse(importlib.metadata.version("bitsandbytes")) >= version.parse(
File "...\Programs\Python\Python310\lib\importlib\metadata_init.py", line 984, in version
return distribution(distribution_name).version
File "...\Programs\Python\Python310\lib\importlib\metadata_init.py", line 957, in distribution
return Distribution.from_name(distribution_name)
File "...\Local\Programs\Python\Python310\lib\importlib\metadata_init_.py", line 548, in from_name
raise PackageNotFoundError(name)
importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes
It seems that bitsandbytes is not working on WIN10. Does anyone know how to fix this?

SMHLondon

Jan 5, 2024

I've got very much the same problem with python 3.9.
transformers package is from git+https://github.com/huggingface/transformers and says version 4.37.0.dev as a version number.
what is funny that the import statement says it loads BitsAndBytes from transformers, but then there exists a package with the same name.
Does one have to install that package additionally?

Vartika1

Mar 21, 2024

I am getting similar error .How is this resolved

ibrahimc

Apr 24, 2024

hey guys is there anyone who resolved the issue?

BDITM

May 10, 2024

I'm also looking at the same issue.

incachild

May 10, 2024

•

edited May 10, 2024

to fix:
pip install bitsandbytes

Colonelblac

Jul 6, 2024

quick fix:
pip install bitsandbytes

srivathsa96

Aug 14, 2024

•

edited Aug 14, 2024

Hello,
I tried by installing bitsandbytes usingpip install bitsandbytes but still getting the same error

ImportError Traceback (most recent call last)
in <cell line: 1>()
----> 1 model= load_quantized_model(model_name)

3 frames
/usr/local/lib/python3.10/dist-packages/transformers/quantizers/quantizer_bnb_4bit.py in validate_environment(self, *args, **kwargs)
64 raise ImportError("Using bitsandbytes 4-bit quantization requires Accelerate: pip install accelerate")
65 if not is_bitsandbytes_available():
---> 66 raise ImportError(
67 "Using bitsandbytes 4-bit quantization requires the latest version of bitsandbytes: pip install -U bitsandbytes"
68 )

ImportError: Using bitsandbytes 4-bit quantization requires the latest version of bitsandbytes: pip install -U bitsandbytes

jiraiya1729

Sep 12, 2024

@srivathsa96 try restarting the kernel it worked for me

heinzketchup

Nov 10, 2024

What kernel? I restarted the linux kernel, and it didn't fix anything.

jiraiya1729

Nov 11, 2024

@heinzketchup i have tried in the colab and restarted the google colab kernel it has worked for me

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