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

Libraries

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

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

pipe = pipeline("text-generation", model="tiiuae/Falcon3-Mamba-7B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-Mamba-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon3-Mamba-7B-Instruct", device_map="auto")
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 Settings

vLLM

How to use tiiuae/Falcon3-Mamba-7B-Instruct 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-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/Falcon3-Mamba-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use tiiuae/Falcon3-Mamba-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/Falcon3-Mamba-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/Falcon3-Mamba-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/Falcon3-Mamba-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/Falcon3-Mamba-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

JingweiZuo commited on Jan 2, 2025

Commit

fc299b4

verified ·

1 Parent(s): 6299176

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ Falcon3-Mamba-7B-Instruct supports a context length up to 32K and was mainly tra
   - state_size: 16
   - 32k context length
   - 65k vocab size
-- Continue Pretrained from [Falcon Mamba 7B](https://huggingface.co/tiiuae/falcon-mamba-7b), with another 1500 Gigatokens of data comprising 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

   - state_size: 16
   - 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