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")
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 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
```

Ollama support

by ayan4m1 - opened Mar 28, 2025

Discussion

ayan4m1

Mar 28, 2025

•

edited Mar 28, 2025

Currently, when loading this model with ollama, the following error is produced (this is CPU inference, GPU inference also fails with a similar error):

Mar 28 15:12:14 bulletlogic.com ollama[2117519]: ggml.c:4484: GGML_ASSERT(ggml_is_matrix(c)) failed
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x3df3c8)[0x5647481303c8]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x3dfa45)[0x564748130a45]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x3e8134)[0x564748139134]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x4e7006)[0x564748238006]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x4ed2e9)[0x56474823e2e9]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x50a7e6)[0x56474825b7e6]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x50f115)[0x564748260115]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x37d1df)[0x5647480ce1df]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: /usr/local/lib/ollama/runners/cpu_avx2/ollama_llama_server(+0x13ebe1)[0x564747e8fbe1]
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: SIGABRT: abort
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: PC=0x7f6610c8bd4c m=4 sigcode=18446744073709551610
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: signal arrived during cgo execution
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: goroutine 36 gp=0xc000106700 m=4 mp=0xc000057508 [syscall]:
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: runtime.cgocall(0x5647480ce190, 0xc000067b78)
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         runtime/cgocall.go:167 +0x4b fp=0xc000067b50 sp=0xc000067b18 pc=0x564747e8252b
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: github.com/ollama/ollama/llama._Cfunc_llama_load_model_from_file(0x7f65b4000c20, {0x0, 0x0, 0x1, 0x0, 0x0, 0x0, 0x5647480cdba0, 0xc000014>Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         _cgo_gotypes.go:691 +0x50 fp=0xc000067b78 sp=0xc000067b50 pc=0x564747f2cd70
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: github.com/ollama/ollama/llama.LoadModelFromFile.func1({0x7ffc519b8d78?, 0x0?}, {0x0, 0x0, 0x1, 0x0, 0x0, 0x0, 0x5647480cdba0, 0xc0000140>Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         github.com/ollama/ollama/llama/llama.go:311 +0x127 fp=0xc000067c78 sp=0xc000067b78 pc=0x564747f2f987
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: github.com/ollama/ollama/llama.LoadModelFromFile({0x7ffc519b8d78, 0x6e}, {0x0, 0x0, 0x0, 0x0, {0x0, 0x0, 0x0}, 0xc000116170, ...})
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         github.com/ollama/ollama/llama/llama.go:311 +0x2d6 fp=0xc000067dc8 sp=0xc000067c78 pc=0x564747f2f676
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: github.com/ollama/ollama/llama/runner.(*Server).loadModel(0xc00013c1b0, {0x0, 0x0, 0x0, 0x0, {0x0, 0x0, 0x0}, 0xc000116170, 0x0}, ...)
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         github.com/ollama/ollama/llama/runner/runner.go:850 +0xc5 fp=0xc000067f10 sp=0xc000067dc8 pc=0x5647480cb605
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: github.com/ollama/ollama/llama/runner.Execute.gowrap1()
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         github.com/ollama/ollama/llama/runner/runner.go:970 +0xda fp=0xc000067fe0 sp=0xc000067f10 pc=0x5647480ccf5a
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: runtime.goexit({})
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000067fe8 sp=0xc000067fe0 pc=0x564747e8ff61
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         github.com/ollama/ollama/llama/runner/runner.go:970 +0xd0d
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         runtime/proc.go:424 +0xce fp=0xc0000277b0 sp=0xc000027790 pc=0x564747e8832e
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: runtime.netpollblock(0x10?, 0x47e20b86?, 0x47?)
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         runtime/netpoll.go:575 +0xf7 fp=0xc0000277e8 sp=0xc0000277b0 pc=0x564747e4d097
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: internal/poll.runtime_pollWait(0x7f65c8a39ef0, 0x72)
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         runtime/netpoll.go:351 +0x85 fp=0xc000027808 sp=0xc0000277e8 pc=0x564747e87625
Mar 28 15:12:14 bulletlogic.com ollama[2117519]: internal/poll.(*pollDesc).wait(0xc000176100?, 0x10?, 0x0)
Mar 28 15:12:14 bulletlogic.com ollama[2117519]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000027830 sp=0xc000027808 pc=0x564747edd467

hanzla

Owner Mar 29, 2025

ollama is not currently supported. will definitely work this one out in the next checkpoint

ayan4m1 changed discussion status to closed Mar 30, 2025

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