lamm-mit/Bioinspired-SmolLM-1.7B-Instruct

Name: Bioinspired-SmolLM-1.7B-Instruct
Rating: 2.5 (13 reviews)

This model was constructed from the SmolLM-1.7B base model using a combination of Continued Pre-training (CPT), Supervised fine-tuning (SFT), and DPO.

The model was trained on a mix of publically available datasets and a corpus of around 5,000 scientific papers in the bio-inspired materials field. During the CPT phase, the raw text of all papers is used. During SFT and ORPO, the model is shown a high-quality mix of question-answer pairs and question-answer-rejected triples, respectively, along with other datasets to train the model for instructions and chat interactions.

Inference

python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

def generate_response(model, tokenizer, text_input="Biology offers amazing materials. Tell me more!", system_prompt='You are a materials scientist.',
                      num_return_sequences=1, temperature=0.3, max_new_tokens=256, do_sample=True,
                      num_beams=1, eos_token_id=[2],
                      device='cuda', top_k=50, top_p=0.9, repetition_penalty=1.1, messages=None, ):

    if messages is None:
        if system_prompt:
            messages = [{"role": "user", "content": system_prompt + text_input}]
        else:
            messages = [{"role": "user", "content": text_input}]
    else:
        messages.append({"role": "user", "content": text_input})

    text_input = tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
    )

    inputs = tokenizer([text_input], add_special_tokens=False, return_tensors='pt').to(device)

    with torch.no_grad():
        outputs = model.generate(
            **inputs, 
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            num_beams=num_beams,
            top_k=top_k,
            do_sample=do_sample,
            top_p=top_p,
            eos_token_id=eos_token_id,
            num_return_sequences=num_return_sequences, 
            repetition_penalty=repetition_penalty,
        )

    outputs = outputs[:, inputs["input_ids"].shape[1]:]

    return tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True), messages            

def load_model(model_name, chat_template=None, compile_mode=None,
               attn_implementation="flash_attention_2", quant=False):
    
    if quant:
        bnb_config4bit = BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_quant_type="nf4",
            bnb_4bit_compute_dtype=torch.bfloat16,
            bnb_4bit_use_double_quant=True,
        )
        model = AutoModelForCausalLM.from_pretrained(
            model_name,
            trust_remote_code=True,
            use_cache=False,
            quantization_config=bnb_config4bit,
            device_map="auto",
            torch_dtype=torch.bfloat16,
            attn_implementation=attn_implementation,
        )
    else:
        model = AutoModelForCausalLM.from_pretrained(
            model_name,
            trust_remote_code=True,
            use_cache=False,
            device_map="auto",
            torch_dtype=torch.bfloat16,
            attn_implementation=attn_implementation,
        )

    if compile_mode:
        model.generation_config.cache_implementation = "static"
        model.forward = torch.compile(model.forward, mode=compile_mode, fullgraph=True)

    tokenizer = AutoTokenizer.from_pretrained(
        model_name, 
        trust_remote_code=True,
        add_bos_token=False
    )

    if chat_template:
        tokenizer.chat_template = chat_template

    return model, tokenizer

Chat template

The model uses the ChatML template, as so (with <|im_end|> as end token):

python

messages = [
    {"role": "system", "content": "You are a biomaterials scientist."},
    {"role": "user", "content": "What is the role of collagen in bone?"},
    {"role": "assistant", "content": "Collagen is a key structural protein."},
]
prompt = tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)
print (prompt)

The output:

raw

<|begin_of_text|><|im_start|>system
You are a biomaterials scientist.<|im_end|>
<|im_start|>user
What is the role of collagen in bone?<|im_end|>
<|im_start|>assistant
Collagen is a key structural protein.<|im_end|>
<|im_start|>assistant

Example use case

Load the model:

model, tokenizer,=load_model (model_name='lamm-mit/Bioinspired-SmolLM-1.7B-Instruct')

Collagen and the Glass Bead Game

python

messages=[]
result,messages=generate_response (model, tokenizer, text_input="Collagen and the Glass Bead Game, discuss their relationship.",
                                   num_return_sequences=1,  temperature=0.3,max_new_tokens=1024 , messages=[]
                                   system_prompt="You are materials scientist. ",)

for res in result:
    print(res, "\n")

messages.append (  {"role": "assistant", "content":result[0]})  

What a fascinating topic! As a materials scientist, I've always been intrigued by the intersection of collagen, a ubiquitous protein in biological systems, and the ancient, strategy-based game, the Glass Bead Game. At first glance, collagen and the Glass Bead Game may seem like vastly different entities. Collagen is a structural protein found in connective tissues, providing strength, flexibility, and support to various biological structures. In contrast, the Glass Bead Game is a strategy board game originating from ancient Mesopotamia, where players navigate a complex, interconnected network of beads and cards to achieve victory. Upon closer inspection, I discovered a surprising connection between these two seemingly disparate entities. The Glass Bead Game, with its intricate, interconnected network of beads and cards, shares a striking similarity with the hierarchical structure of collagen. Both are composed of smaller, interconnected units that form a larger, more complex system. In collagen, the repeating unit of amino acids, glycine, proline, and hydroxyproline, creates a hierarchical structure that contributes to its mechanical properties. Similarly, the Glass Bead Game's beads and cards are arranged in a hierarchical manner, with each component influencing the overall gameplay and strategy. The Glass Bead Game's "beads" represent the individual components, while the "cards" symbolize the interactions and relationships between these components. Furthermore, both collagen and the Glass Bead Game exhibit self-assembly and hierarchical organization. Collagen molecules self-assemble into fibrils, which then form larger structures, such as fibers and tissues. The Glass Bead Game, too, relies on the strategic arrangement of beads and cards to create a cohesive, interconnected system. The game's rules and strategies are designed to facilitate the assembly and interaction of its components, much like the self-assembly of collagen molecules. Moreover, the concept of "interconnectedness" is a crucial aspect of both collagen and the Glass Bead Game. In collagen, the interconnected fibrils provide structural integrity and enable the transfer of mechanical loads. In the Glass Bead Game, the interconnected network of beads and cards creates a dynamic, ever-changing system that requires players to adapt and respond to the shifting relationships between components. In conclusion, the relationship between collagen and the Glass Bead Game is one of shared principles and concepts. Both entities exhibit hierarchical structure, self-assembly, and interconnectedness, which are essential for their respective functions. By recognizing these parallels, we can gain a deeper understanding of the fundamental principles that govern the behavior of biological systems and the strategic complexities of games like the Glass Bead Game.

You can ask a follow-up question like so:

python

result,messages=generate_response (model, tokenizer, text_input="Summarize the key points in JSON format.",num_return_sequences=1, 
                                   temperature=0.3,max_new_tokens=1024 , messages=messages)

for res in result:
    print(res, "\n")

messages.append (  {"role": "assistant", "content":result[0]})

<pre style="white-space: pre-wrap;">

Here's a summary of collagen and the Glass Bead Game in JSON format:

```json
{
  "collagen": {
    "structure": "proteinous fibrous network",
    "composition": "glycoprotein",
    "properties": "high tensile strength, low stiffness",
    "functions": "structural support, cell signaling, wound healing",
    "types": ["alpha", "beta", "gamma", "delta"]
  },
  "glass bead game": {
    "rules": "a strategy game where players collect and trade glass beads, simulating the process of collagen synthesis and mineralization",
    "components": ["glass beads", "mineral deposits", "cell signaling molecules", "growth factors"],
    "goal": "collect and trade the most beads to achieve mineralization and growth",
    "rules of play": "players must collect beads, deposit them in cells, and stimulate mineralization through signaling molecules and growth factors",
    "game mechanics": "players earn points for successful mineralization, trade beads for resources, and manage their cells' mineralization and growth rates"
  },
}

In this JSON representation, collagen is a proteinous fibrous network with a high tensile strength and low stiffness, while the Glass Bead Game is a strategy game where players collect and trade glass beads to simulate the process of collagen synthesis and mineralization. The Glass Bead Game components include glass beads, mineral deposits, cell signaling molecules, and growth factors, with the goal of collecting and trading the most beads to achieve mineralization and growth. The rules of play involve collecting beads, depositing them in cells, and stimulating mineralization through signaling molecules and growth factors.

Benchmark

Performance on the bioinspired benchmark (testing with domain questions to assess performance relative to the training corpus around biological materials and spider silk):

Citation

Please cite as:

bibtex

@article{LuLuuBuehler2024,
  title={Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities},
  author={Wei Lu and Rachel K. Luu and Markus J. Buehler},
  journal={arXiv: https://arxiv.org/abs/2409.03444},
  year={2024},
}

@article{LuuBuehler2023bioinspiredLLM,
  title={BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-Inspired Materials},
  author={Rachel K. Luu and Markus J. Buehler},
  year={2023},
  journal={Advanced Science},
  doi={10.1002/advs.202306724},
  eprint={2309.08788},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2309.08788}
}

@article{Buehler2024XLoRA,
  title={X-LoRA: Mixture of low-rank adapter experts, a flexible framework for large language models with applications in protein mechanics and molecular design},
  author={Eric L. Buehler and Markus J. Buehler},
  year={2024},
  journal={APL Machine Learning},
  volume={2},
  number={2},
  pages={026119},
  doi={10.1063/5.0203126},
  note={\url{https://doi.org/10.1063/5.0203126}}
}