Menu
Home
About
Our Role
Goals
The Team
Roadmap
Tokenomics
How To Buy
Knowledge Base
Contacts
Sitemap & Links
A.I.
Chart
Shop
IMMORTALITY
🏠
⬇️
LumenScopeAI BrainTransformers
New name
B
I
U
S
link
image
code
HTML
list
Show page
Syntax
* git clone https://github.com/LumenScopeAI/BrainTransformers-SNN-LLM.git * https://huggingface.co/LumenscopeAI/BrainTransformers-3B-Chat Custom transfomer that comes with git clone: BrainTransformers-SNN-LLM/transformers/models/braingpt/configuration_braingpt.py Add: {pre} from transformers import PretrainedConfig {/pre} {pre} git clone https://github.com/LumenScopeAI/BrainTransformers-SNN-LLM.git cd BrainTransformers-SNN-LLM/ python3 -m venv venv source venv/bin/activate pip install -r requirements.txt sudo apt-get install git-lfs git lfs install git clone https://huggingface.co/LumenscopeAI/BrainTransformers-3B-Chat {/pre} BrainTransformers-SNN-LLM/transformers/models/braingpt/modeling_braingpt.py {pre} def load_silu_approximator(device, dtype): act_fn = SiLUApproximator().to(device).to(dtype) pos_checkpoint = os.path.join(os.path.dirname(__file__), 'model_pos.pth') neg_checkpoint = os.path.join(os.path.dirname(__file__), 'model_neg.pth') if os.path.exists(pos_checkpoint) and os.path.exists(neg_checkpoint): act_fn.pos_model.load_state_dict( torch.load(pos_checkpoint, map_location=device, weights_only=True) ) act_fn.neg_model.load_state_dict( torch.load(neg_checkpoint, map_location=device, weights_only=True) ) """ act_fn.pos_model.load_state_dict( torch.load(pos_checkpoint, map_location=device) ) act_fn.neg_model.load_state_dict( torch.load(neg_checkpoint, map_location=device) ) """ else: raise FileNotFoundError( f"SiLUApproximator parameters not found at {pos_checkpoint} and {neg_checkpoint}" ) return act_fn {/pre} Open run.py and change the model path to BrainTransformers-3B-Chat {pre} import torch from transformers import AutoTokenizer, BrainGPTForCausalLM from tqdm import tqdm from torch.utils.data import DataLoader # Define the model and tokenizer path model_path = "BrainTransformers-3B-Chat" # Load the model and tokenizer print("Loading model and tokenizer...") model = BrainGPTForCausalLM.from_pretrained(model_path) tokenizer = AutoTokenizer.from_pretrained(model_path) # Move the model to GPU (if available) device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model.to(device) print(f"Model loaded on {device}") # Define a function to generate text def generate_text(messages, max_new_tokens=200, temperature=0.7, top_k=50, top_p=0.95, do_sample=True): text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(device) with torch.no_grad(): generated_ids = model.generate( **model_inputs, max_new_tokens=max_new_tokens, temperature=temperature, top_k=top_k, top_p=top_p, do_sample=do_sample, pad_token_id=tokenizer.eos_token_id ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] return response # Test the generation function def test_generation(test_prompts): print("\nTesting text generation:") for prompt in test_prompts: messages = [ {"role": "system", "content": "You are a knowledgeable assistant."}, {"role": "user", "content": prompt} ] print(f"\nPrompt: {prompt}") generated = generate_text(messages) print(f"Generated: {generated}") # Define a function to interact with the model def interact_with_model(): while True: user_input = input("You: ") if user_input.lower() in ["exit", "quit"]: break messages = [ {"role": "system", "content": "You are a knowledgeable assistant."}, {"role": "user", "content": user_input} ] response = generate_text(messages) print(f"Assistant: {response}") test_prompts = [ "Please explain the Pythagorean theorem!", "What is artificial intelligence?", "Write a poem about spring.", "Explain the basic principles of quantum computing.", "How to make a simple pizza?" ] print("\nTesting text generation before STDP training:") test_generation(test_prompts) # Interact with the model print("\nYou can now interact with the model. Type 'exit' or 'quit' to stop.") interact_with_model() {/pre}
Password
Summary of changes
📜
⏱️
⬆️