Instructions to use MorphMind-AI/CFM-Methods-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MorphMind-AI/CFM-Methods-3B with Transformers:

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

pipe = pipeline("text-generation", model="MorphMind-AI/CFM-Methods-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MorphMind-AI/CFM-Methods-3B")
model = AutoModelForCausalLM.from_pretrained("MorphMind-AI/CFM-Methods-3B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MorphMind-AI/CFM-Methods-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MorphMind-AI/CFM-Methods-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MorphMind-AI/CFM-Methods-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MorphMind-AI/CFM-Methods-3B

SGLang

How to use MorphMind-AI/CFM-Methods-3B 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 "MorphMind-AI/CFM-Methods-3B" \
    --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": "MorphMind-AI/CFM-Methods-3B",
		"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 "MorphMind-AI/CFM-Methods-3B" \
        --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": "MorphMind-AI/CFM-Methods-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MorphMind-AI/CFM-Methods-3B with Docker Model Runner:
```
docker model run hf.co/MorphMind-AI/CFM-Methods-3B
```

Joe-Davis commited on Jun 12

Commit

9139aab

verified ·

1 Parent(s): c6aa3fa

Drop on-prem label

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -38,7 +38,7 @@ given JSON output and an adequate token budget, so the comparison is like-for-li
 | base Qwen2.5-3B (zero-shot) | 0.04 | 3B |
 | Claude Opus 4.8 | 0.61 | frontier |
 | GPT-5.4 | 0.84 | frontier |
-| **CFM-Proof-3B (ours)** | **0.88** | **3B · on-prem** |
 On this held-out sample CFM-Proof-3B is **competitive with frontier models on error catch-rate at roughly
 1/100 the size, running on a single GPU.** On the **full** 1,977-proof test and an **entirely held-out

 | base Qwen2.5-3B (zero-shot) | 0.04 | 3B |
 | Claude Opus 4.8 | 0.61 | frontier |
 | GPT-5.4 | 0.84 | frontier |
+| **CFM-Proof-3B (ours)** | **0.88** | **3B · single GPU** |
 On this held-out sample CFM-Proof-3B is **competitive with frontier models on error catch-rate at roughly
 1/100 the size, running on a single GPU.** On the **full** 1,977-proof test and an **entirely held-out