Instructions to use tiiuae/Falcon3-Mamba-7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon3-Mamba-7B-Base with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon3-Mamba-7B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-Mamba-7B-Base")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon3-Mamba-7B-Base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tiiuae/Falcon3-Mamba-7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon3-Mamba-7B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon3-Mamba-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon3-Mamba-7B-Base

SGLang

How to use tiiuae/Falcon3-Mamba-7B-Base 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/Falcon3-Mamba-7B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon3-Mamba-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/Falcon3-Mamba-7B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon3-Mamba-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tiiuae/Falcon3-Mamba-7B-Base with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon3-Mamba-7B-Base
```

devingulliver commited on Jun 26, 2025

Commit

0bdc7ca

verified ·

1 Parent(s): 3c64bd0

Update README.md

Browse files

This is the base model, it was not instruct trained.

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -32,7 +32,6 @@ Falcon3-Mamba-7B-Base supports a context length up to 32K and was mainly trained
   - 32k context length
   - 65k vocab size
 - Continue Pretrained from [Falcon-Mamba-7b](https://arxiv.org/abs/2410.05355), with another 1500 Gigatokens of data consisting of web, code, STEM and high quality data.
-- Postrained on 1.2 million samples of STEM, conversations, code, and safety.
 - Developed by [Technology Innovation Institute](https://www.tii.ae)
 - License: TII Falcon-LLM License 2.0
 - Model Release Date: December 2024

   - 32k context length
   - 65k vocab size
 - Continue Pretrained from [Falcon-Mamba-7b](https://arxiv.org/abs/2410.05355), with another 1500 Gigatokens of data consisting of web, code, STEM and high quality data.
 - Developed by [Technology Innovation Institute](https://www.tii.ae)
 - License: TII Falcon-LLM License 2.0
 - Model Release Date: December 2024