metadata
language:
- multilingual
- en
license: apache-2.0
library_name: transformers
tags:
- nlp
- code
- vision
- chemistry
- engineering
- biology
- bio-inspired
- text-generation-inference
- materials science
- mixture-of-experts
- science
- latex
datasets:
- lamm-mit/Cephalo-Bioinspired-Mechanics-Materials
- lamm-mit/Cephalo-Wikipedia-Materials
- OleehyO/latex-formulas
- lamm-mit/OleehyO-latex-formulas
pipeline_tag: image-text-to-text
inference:
parameters:
temperature: 0.3
widget:
- messages:
- role: user
content: <|image_1|>Can you describe what you see in the image?
Model Summary
Cephalo is a series of multimodal materials science focused vision large language models (V-LLMs) designed to integrate visual and linguistic data for advanced understanding and interaction in human-AI or multi-agent AI frameworks.
The model is developed to process diverse inputs, including images and text, facilitating a broad range of applications such as image captioning, visual question answering, and multimodal content generation. The architecture combines a vision encoder model and an autoregressive transformer to process complex natural language understanding.
Cephalo provides a robust framework for multimodal interaction and understanding, including the development of complex generative pipelines to create 2D and 3D renderings of material microstructures as input for additive manufacturing methods.
This version of Cephalo, lamm-mit/Cephalo-Idefics2-3x8b-beta, is a Mixture-of-Expert model based on variants and fine-tuned versions of the Idefics-2 model. The basic model architecture is as follows:
The model has 20b parameters (3 experts, each 8b each, 8b active parameters during inference).
Download Idefics-2 MoE Model and Sample inference code
pip install transformers -U
import torch
from transformers import AutoModelForCausalLM, AutoProcessor, AutoConfig
def count_parameters(model):
total_params = sum(p.numel() for p in model.parameters())
trainable_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
#number of parameters in b
return total_params/1e9, trainable_params/1e9
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_name_moe = f"lamm-mit/Cephalo-Idefics2-3x8b-beta"
config = AutoConfig.from_pretrained(model_name_moe, trust_remote_code=True)
processor = AutoProcessor.from_pretrained(model_name_moe, trust_remote_code=True)
moe_model = AutoModelForCausalLM.from_pretrained(
model_name_moe,config=config,
trust_remote_code=True, torch_dtype=torch.bfloat16,
# quantization_config=quantization_config,
).to(device)
count_parameters(moe_model)
Now use downloaded model for inference:
from transformers.image_utils import load_image
DEVICE='cuda'
image = load_image("https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg")
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
# Get inputs using the processor
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = moe_model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
Make a Idefics-2-MoE model from scratch using several pre-trained models
Download .py files that implement the Phi-3-V and the Mixture-of-Expert Vision model
pip install huggingface_hub
from huggingface_hub import HfApi, hf_hub_download
from tqdm.notebook import tqdm
import os
import shutil
# Repository details
repo_id = "lamm-mit/Cephalo-Idefics2-3x8b-beta"
api = HfApi()
# List all files in the repository
files_in_repo = api.list_repo_files(repo_id)
# Filter for .py files
py_files = [file for file in files_in_repo if file.endswith('.py')]
# Directory to save the downloaded files
save_dir = "./Idefics2_MoE/"
os.makedirs(save_dir, exist_ok=True)
# Download each .py file
for file_name in tqdm(py_files):
file_path = hf_hub_download(repo_id=repo_id, filename=file_name)
new_path = os.path.join(save_dir, file_name)
shutil.move(file_path, new_path)
print(f"Downloaded: {file_name}")
print("Download completed.")
Download models that will form the experts, as well as the base model:
from transformers import AutoProcessor, Idefics2ForConditionalGeneration , AutoTokenizer
from transformers import BitsAndBytesConfig
DEVICE='cuda'
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
model_id_1='lamm-mit/Cephalo-Idefics-2-vision-8b-beta'
model_1 = Idefics2ForConditionalGeneration.from_pretrained( model_id_1,
torch_dtype=torch.bfloat16, #if your GPU allows
_attn_implementation="flash_attention_2", #make sure Flash Attention 2 is installed
trust_remote_code=True,
#quantization_config=quantization_config,
)
processor = AutoProcessor.from_pretrained(
f"{model_id_1}",
do_image_splitting=True
)
config = AutoConfig.from_pretrained(model_id_1, trust_remote_code=True)
IDEFICS2_CHAT_TEMPLATE = "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
processor.chat_template = IDEFICS2_CHAT_TEMPLATE
Now, load the rest of the models:
model_id_2='HuggingFaceM4/idefics2-8b-chatty'
model_2 = Idefics2ForConditionalGeneration.from_pretrained( model_id_2,
torch_dtype=torch.bfloat16, #if your GPU allows
_attn_implementation="flash_attention_2", #make sure Flash Attention 2 is installed
trust_remote_code=True,
#quantization_config=quantization_config,
)
model_id_3='HuggingFaceM4/idefics2-8b'
model_3 = Idefics2ForConditionalGeneration.from_pretrained( model_id_3,
torch_dtype=torch.bfloat16, #if your GPU allows
_attn_implementation="flash_attention_2", #make sure Flash Attention 2 is installed
trust_remote_code=True,
#quantization_config=quantization_config,
)
Put on device:
model_1.to(DEVICE)
model_2.to(DEVICE)
model_3.to(DEVICE)
Construct MoE
Here we show how a MoE is constructed from the set of expert models loaded earlier. We consider three models, model_1, model_2 and model_3.
dtype = torch.bfloat16 # Desired dtype for new layers
base_model = copy.deepcopy(model_1) # Your base model
expert_models = [ model_1, model_2, model_3 ] # List of expert models
moe_config = Idefics2ForCausalLMMoEConfig(config=config, k=1, num_expert_models=len (expert_models))
moe_model = Idefics2ForCausalLMMoE(moe_config, base_model, expert_models, layer_dtype = dtype)
count_parameters(expert_models[0]),count_parameters(moe_model)
Delete models no longer needed:
del model_1
del model_2
del model_3
Put MoE model on device:
moe_model.to(DEVICE)
Test if it works (untrained, may not produce desirable putput since gating layers have not been trained):
from transformers.image_utils import load_image
image = load_image("https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg")
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
# Get inputs using the processor
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = moe_model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
Now train MoE gating function
We train the gating layers by providing sample images/prompts for each of the three experts. Here is a simple example training set:
image_1 = Image.open("./VALIDATION/Q15.jpg")
image_1a = Image.open("./VALIDATION/Q31.jpg")
image_2 = Image.open(requests.get("https://media.wired.com/photos/5aa32b912ba43111d1213e0c/master/w_2240,c_limit/akhacouple.jpg", stream=True).raw)
image_2a = Image.open(requests.get("https://media.wired.com/photos/5aa32b912ba43111d1213e0c/master/w_2240,c_limit/akhacouple.jpg", stream=True).raw)
image_3 = Image.open(requests.get("https://i5.walmartimages.com/seo/Amazing-Andrea-Apple-Tree-Seeds-20-Seeds-Grow-Fresh-Apples_ff218043-bcd4-4437-8418-6631d8e97bb3.638ac0120ff05c8913e85ebb74f45f6c.jpeg?odnHeight=640&odnWidth=640&odnBg=FFFFFF", stream=True).raw)
image_3a = Image.open(requests.get("https://i5.walmartimages.com/seo/Amazing-Andrea-Apple-Tree-Seeds-20-Seeds-Grow-Fresh-Apples_ff218043-bcd4-4437-8418-6631d8e97bb3.638ac0120ff05c8913e85ebb74f45f6c.jpeg?odnHeight=640&odnWidth=640&odnBg=FFFFFF", stream=True).raw)
prompts_per_expert = [
[{"text": "User:<image>What is shown in this image. Explain the importance for materials design.<end_of_utterance>Assistant: The image shows", "image": [image_1]},
{"text": "User:<image>What is shown in this image. Explain the importance for materials design.<end_of_utterance>Assistant: The image shows", "image": [image_1a]},
],
[{"text": "User:<image>What is shown in this image. <end_of_utterance>Assistant: The image shows a human.", "image": [image_2]},
{"text": "User:<image>What is shown in this image, and what does it mean in terms of human history? <end_of_utterance>Assistant: The image shows a historical image of human development.", "image": [image_2a]},
],
[{"text": "User:<image>What is shown in this image. Provide a brief answer. <end_of_utterance>Assistant: This is an apple.", "image": [image_3]},
{"text": "User:<image>What is shown in this image. Brief and concise answer. <end_of_utterance>Assistant: The image shows an apple.", "image": [image_3a]},
],
]
gating_layer_params = moe_model.train_gating_layer_params_from_hidden_states(processor, prompts_per_expert,
epochs=1000, loss_steps=100, lr=5e-5, layer_offset=0)
# Set parameters for a specific layer
moe_model.set_gating_layer_params(gating_layer_params)
Now that the MoE model has been trained, we can try inference. Inference after MoE gating layers are trained:
from transformers.image_utils import load_image
image = load_image("https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg")
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
# Get inputs using the processor
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = moe_model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
Push to hub and save locally
We can save the MoE model either in Hugging Face Hub or locally:
repo_id='...'
moe_name='Cephalo-Idefics2-3x8b-beta'
processor.push_to_hub (f'{repo_id}/'+moe_name, )
moe_model.push_to_hub (f'{repo_id}/'+merged_name, )
Save locally:
processor.save_pretrained(moe_name, )
moe_model.save_pretrained(moe_name, )
Loading the model works as done above. Here included again for completeness:
model_name_moe = f'{repo_id}/'+moe_name
config = AutoConfig.from_pretrained(model_name_moe, trust_remote_code=True)
processor = AutoProcessor.from_pretrained(model_name_moe, trust_remote_code=True)
moe_model = AutoModelForCausalLM.from_pretrained(
model_name_moe,config=config,
trust_remote_code=True, torch_dtype=torch.bfloat16,
# quantization_config=quantization_config,
).to(device)
count_parameters(moe_model)