Instructions to use lamm-mit/Graph-Preflexor-8b_12292025 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lamm-mit/Graph-Preflexor-8b_12292025 with Transformers:

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

pipe = pipeline("text-generation", model="lamm-mit/Graph-Preflexor-8b_12292025")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lamm-mit/Graph-Preflexor-8b_12292025")
model = AutoModelForCausalLM.from_pretrained("lamm-mit/Graph-Preflexor-8b_12292025")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lamm-mit/Graph-Preflexor-8b_12292025 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lamm-mit/Graph-Preflexor-8b_12292025"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lamm-mit/Graph-Preflexor-8b_12292025",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lamm-mit/Graph-Preflexor-8b_12292025

SGLang

How to use lamm-mit/Graph-Preflexor-8b_12292025 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 "lamm-mit/Graph-Preflexor-8b_12292025" \
    --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": "lamm-mit/Graph-Preflexor-8b_12292025",
		"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 "lamm-mit/Graph-Preflexor-8b_12292025" \
        --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": "lamm-mit/Graph-Preflexor-8b_12292025",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lamm-mit/Graph-Preflexor-8b_12292025 with Docker Model Runner:
```
docker model run hf.co/lamm-mit/Graph-Preflexor-8b_12292025
```

mjbuehler commited on Dec 29, 2025

Commit

6d38791

verified ·

1 Parent(s): b9dbe5d

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -9

README.md CHANGED Viewed

@@ -72,12 +72,11 @@ This makes the model particularly suitable for **AI-for-science**, **graph-nativ
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
-#token= 'hf_...'
 # ------------------------------------------------------------------------------
 # Configuration
 # ------------------------------------------------------------------------------
 MODEL_NAME = "lamm-mit/Graph-Preflexor-8b_12292025"
 PROMPT = "Give me a short introduction to materiomics."
 MAX_NEW_TOKENS = 32_768
@@ -86,25 +85,21 @@ THINK_END_TOKEN_ID = 151668  # </think>
 # ------------------------------------------------------------------------------
 # Model & Tokenizer Loading
 # ------------------------------------------------------------------------------
 tokenizer = AutoTokenizer.from_pretrained(
     MODEL_NAME,
     token=token,
 )
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     torch_dtype="auto",
     device_map="auto",
     token=token,
 )
 model.eval()
 # ------------------------------------------------------------------------------
 # Prompt Construction
 # ------------------------------------------------------------------------------
 messages = [
     {"role": "user", "content": PROMPT}
 ]
@@ -124,7 +119,6 @@ model_inputs = tokenizer(
 # ------------------------------------------------------------------------------
 # Generation
 # ------------------------------------------------------------------------------
 gen_config = GenerationConfig(
     max_new_tokens=MAX_NEW_TOKENS,
     do_sample=True,  # sample
@@ -143,7 +137,6 @@ output_ids = generated[0, model_inputs.input_ids.shape[1]:].tolist()
 # ------------------------------------------------------------------------------
 # Thinking / Content Parsing
 # ------------------------------------------------------------------------------
 def split_thinking(output_ids, tokenizer, think_end_id):
     """
     Split generated tokens into (thinking, final_content) based on </think>.
@@ -176,7 +169,6 @@ thinking, content = split_thinking(
 # ------------------------------------------------------------------------------
 # Output
 # ------------------------------------------------------------------------------
 print("\n" + "=" * 80)
 print("THINKING")
 print("=" * 80)
@@ -253,6 +245,8 @@ FINAL OUTPUT
 Materiomics is an interdisciplinary field that merges materials science with omics methodologies—such as genomics, proteomics, and metabolomics—to systematically analyze, design, and predict the properties of materials at atomic and molecular scales. At its core, materiomics leverages high-throughput experimental techniques and advanced computational models to generate vast datasets on material composition, structure, processing conditions, and resulting properties. These data are then used to build predictive models that can forecast material behavior under various stimuli, enabling the rational design of novel materials with tailored functionalities. Key phenomena underpinning materiomics include self-assembly processes where molecules spontaneously form ordered structures, phase transitions that dictate stability and transformation under thermal or mechanical stress, and defect engineering that manipulates imperfections to enhance properties like strength or conductivity. By drawing inspiration from biological systems—where complex materials like proteins and cell membranes emerge from simple building blocks—materiomics adopts data-driven, systems-level approaches to accelerate discovery. This field is pivotal in advancing nanotechnology, sustainable materials, and AI-driven R&D, offering a scalable framework to move beyond traditional trial-and-error methods, thereby revolutionizing industries from electronics to energy storage.
 ```
 # References and Citation
 This model was trained based on the ideas presented in the below referenced papers.

 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+token= 'hf_...'
 # ------------------------------------------------------------------------------
 # Configuration
 # ------------------------------------------------------------------------------
 MODEL_NAME = "lamm-mit/Graph-Preflexor-8b_12292025"
 PROMPT = "Give me a short introduction to materiomics."
 MAX_NEW_TOKENS = 32_768
 # ------------------------------------------------------------------------------
 # Model & Tokenizer Loading
 # ------------------------------------------------------------------------------
 tokenizer = AutoTokenizer.from_pretrained(
     MODEL_NAME,
     token=token,
 )
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     torch_dtype="auto",
     device_map="auto",
     token=token,
 )
 model.eval()
 # ------------------------------------------------------------------------------
 # Prompt Construction
 # ------------------------------------------------------------------------------
 messages = [
     {"role": "user", "content": PROMPT}
 ]
 # ------------------------------------------------------------------------------
 # Generation
 # ------------------------------------------------------------------------------
 gen_config = GenerationConfig(
     max_new_tokens=MAX_NEW_TOKENS,
     do_sample=True,  # sample
 # ------------------------------------------------------------------------------
 # Thinking / Content Parsing
 # ------------------------------------------------------------------------------
 def split_thinking(output_ids, tokenizer, think_end_id):
     """
     Split generated tokens into (thinking, final_content) based on </think>.
 # ------------------------------------------------------------------------------
 # Output
 # ------------------------------------------------------------------------------
 print("\n" + "=" * 80)
 print("THINKING")
 print("=" * 80)
 Materiomics is an interdisciplinary field that merges materials science with omics methodologies—such as genomics, proteomics, and metabolomics—to systematically analyze, design, and predict the properties of materials at atomic and molecular scales. At its core, materiomics leverages high-throughput experimental techniques and advanced computational models to generate vast datasets on material composition, structure, processing conditions, and resulting properties. These data are then used to build predictive models that can forecast material behavior under various stimuli, enabling the rational design of novel materials with tailored functionalities. Key phenomena underpinning materiomics include self-assembly processes where molecules spontaneously form ordered structures, phase transitions that dictate stability and transformation under thermal or mechanical stress, and defect engineering that manipulates imperfections to enhance properties like strength or conductivity. By drawing inspiration from biological systems—where complex materials like proteins and cell membranes emerge from simple building blocks—materiomics adopts data-driven, systems-level approaches to accelerate discovery. This field is pivotal in advancing nanotechnology, sustainable materials, and AI-driven R&D, offering a scalable framework to move beyond traditional trial-and-error methods, thereby revolutionizing industries from electronics to energy storage.
 ```
+![image](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/iTrRAeKbE1GNQeA6Bugu5.png)
 # References and Citation
 This model was trained based on the ideas presented in the below referenced papers.