tiiuae
/

falcon-7b-instruct

Text Generation

text-generation-inference

Model card Files Files and versions

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

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

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
```

Resources

View closed (37)

Custom 4-bit Finetuning 5-7 times faster inference than QLora

#13 opened almost 3 years ago by

Example Use

#1 opened almost 3 years ago by

Update README.md

#132 opened 4 months ago by

Request: DOI

#131 opened 4 months ago by

Request: DOI

#130 opened 4 months ago by

i want the API for this model to use it on college project but can't find a way to do it

#128 opened about 1 year ago by

Installation Guide

#127 opened about 1 year ago by

429 Client Error: Too Many Requests for url

#123 opened over 1 year ago by

Interview request: genAI evaluation & documentation

#122 opened over 1 year ago by

Finetuning with Bengali Dataset Fails : Need Urgent Help ?

#121 opened almost 2 years ago by

Vision to text capabilities

#120 opened about 2 years ago by

ValueError: Error raised by inference API: Cannot override task for LLM models

#119 opened about 2 years ago by

joangonzaleezzz

[AUTOMATED] Model Memory Requirements

#118 opened about 2 years ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#117 opened about 2 years ago by

model-sizer-bot

422 Unprocessable Entity when trying to use conversational API

#116 opened about 2 years ago by

torch.cuda.OutOfMemoryError: CUDA out of memory.

#115 opened over 2 years ago by

Update for langchain

#113 opened over 2 years ago by

Update README.md

#112 opened over 2 years ago by

Can Falcon have supported UTF-8?

#110 opened over 2 years ago by

No package metadata was found for bitsandbytes

#109 opened over 2 years ago by

Adding Evaluation Results

#108 opened over 2 years ago by

leaderboard-pr-bot

Compare Multiple Document using this model.

#104 opened over 2 years ago by

Upload model

#103 opened over 2 years ago by

Reasearch team in Nile university.

#101 opened over 2 years ago by

This is an instruct model, which may not be ideal for further finetuning.

#100 opened over 2 years ago by

tiiuae/falcon-7b-instruct does not appear to have a file named config.json

#99 opened over 2 years ago by

falcon-7b-instruct responds with weird and short answers ?

#98 opened over 2 years ago by

model not generating text

#97 opened over 2 years ago by

Trying to deploy this using Inference Endpoints

#96 opened over 2 years ago by

Code for using inference api

#94 opened over 2 years ago by

Inference Api

#93 opened over 2 years ago by

The correctness of the result using transformers apply_chat_template

#92 opened over 2 years ago by

Request: DOI

#91 opened over 2 years ago by

How is falcon able to generate indic token , when it is not trained on Indic languages. even tokenizer.json doest have any Indic tokens.

#90 opened over 2 years ago by

How to solve this issue?

#87 opened over 2 years ago by

Update generation_config.json

#86 opened over 2 years ago by

Adding `safetensors` variant of this model

#84 opened over 2 years ago by

Hardware requirements on falcon models: 7B, 40B, 180B

#83 opened over 2 years ago by

Switching Falcon to other language

#82 opened over 2 years ago by

Update config.json

#81 opened over 2 years ago by

'num_return_sequences' & 'num_beams' can't be changed in inference API calls

#80 opened over 2 years ago by

Adding `safetensors` variant of this model

#79 opened over 2 years ago by

Facing Issues with Model Output and Inference Times

#78 opened over 2 years ago by

License file

#77 opened over 2 years ago by

Share your recommended configurations for speed.

#76 opened over 2 years ago by

Adding `safetensors` variant of this model

#75 opened over 2 years ago by

Use input attention mask instead of casual mask in attention

#74 opened almost 3 years ago by

Merge SentenceTransformer with Falcon-7b-instruct

#73 opened almost 3 years ago by

integration issue with Langchain csv agent

#71 opened almost 3 years ago by

Issue with Falcon LLM while trying to use it on AWS EC2 Inferentia 2.8xlarge Instance

#70 opened almost 3 years ago by