Instructions to use hanzla/Falcon3-Mamba-R1-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hanzla/Falcon3-Mamba-R1-v0 with Transformers:

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

pipe = pipeline("text-generation", model="hanzla/Falcon3-Mamba-R1-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hanzla/Falcon3-Mamba-R1-v0")
model = AutoModelForCausalLM.from_pretrained("hanzla/Falcon3-Mamba-R1-v0", 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 hanzla/Falcon3-Mamba-R1-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hanzla/Falcon3-Mamba-R1-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hanzla/Falcon3-Mamba-R1-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hanzla/Falcon3-Mamba-R1-v0

SGLang

How to use hanzla/Falcon3-Mamba-R1-v0 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 "hanzla/Falcon3-Mamba-R1-v0" \
    --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": "hanzla/Falcon3-Mamba-R1-v0",
		"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 "hanzla/Falcon3-Mamba-R1-v0" \
        --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": "hanzla/Falcon3-Mamba-R1-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hanzla/Falcon3-Mamba-R1-v0 with Docker Model Runner:
```
docker model run hf.co/hanzla/Falcon3-Mamba-R1-v0
```

hanzla commited on Mar 15, 2025

Commit

4a410ad

verified ·

1 Parent(s): 3b5b4ac

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -10

README.md CHANGED Viewed

@@ -1,6 +1,12 @@
 ---
 library_name: transformers
-tags: []
 ---
 # Model Card for Model ID
@@ -13,17 +19,14 @@ tags: []
 ### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
 ### Model Sources [optional]

 ---
 library_name: transformers
+tags:
+- mamba
+- falcon3
+- reasoning
+base_model:
+- tiiuae/Falcon3-Mamba-7B-Instruct
+pipeline_tag: text-generation
 ---
 # Model Card for Model ID
 ### Model Description
+This model is a fine tuned version of Falcon3 Mamba 7 billion instruct.
+It is tailored to reason and build logic before answering to the user question. The Mamba based model scales linearly with increased number of tokens, making it a very fast reasoner while maintaining consistent response quality.
+This is from an earlier checkpoint of the model training.
+- **Developed by:** Hanzla Javaid
+- **Model type:** Mamba
 ### Model Sources [optional]