You can deploy this model and start earning money today!

insilicomedicine/
C3LM

Name: C3LM
Availability: InStock

single-step-retrosynthesis

Views

No views yet

C3LM

Chemistry Constraint–Consistent Language Model

Paper

ChemCensor

Overview

C3LM is a chemistry-focused language model for Single-Step Retrosynthesis task. This checkpoint was initialized from LFM2-2.6B and trained with supervised fine-tuning (SFT) on a combined CREED + USPTO-full dataset.

Load model

python

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "insilicomedicine/C3LM"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
#    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

Usage example

python

import re

ATOM_TOKENS = ["Ag","Al","As","Au","Bi","Br","Ca","Cl","Cr","Cu","Fe","Ga","Gd","Ge","Hg","Li","Mg","Mo","Na","Pt","Ru","Sb","Se","Si","Sn","Sc","B","C","F","H","I","K","M","N","O","P","S","V","W","Z","c","e","n","o","p","s"]

SMI_REGEX_PATTERN = (
    r"(\[|\]|\(|\)|\.|=|#|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9]|"
    + "|".join(ATOM_TOKENS)
    + ")"
)
smi_regex = re.compile(SMI_REGEX_PATTERN)

def isolate_sequence(s):
    return "".join(["<sm_" + tok + ">" for tok in smi_regex.findall(s)])

def deisolate_sequence(s):
    s = re.sub("[<\s]?sm_[^>]+>", lambda matchobj: matchobj.group(0)[4:-1], s).strip()
    return s

# Prepare prompts
product_smiles = "N1C(=O)Cc2ccc(Nc3ccc(N[C@@H]4CN(C(c5cc(NCCO)ccc5)=O)C[C@@H]4c4scnc4)cc3)cc21"
prompt = f"What are the possible reactants that could have formed the following product <smiles>{isolate_sequence(product_smiles)}</smiles>? Wrap an answer in <smiles> tags/think"

input_ids = tokenizer.apply_chat_template(
    [
        {"role": "system", "content": "You are a helpful assistant in chemistry and biology."},
        {"role": "user", "content": prompt}
    ],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
)['input_ids'].to(model.device)

# Generate answer
output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

for out in output:
    out = tokenizer.decode(out, skip_special_tokens=False)
    answer_part = out.split('</think>')[1].split('<smiles>')[1].split('</smiles>')[0]
    answer_part = deisolate_sequence(answer_part)
    print('Reactants: ', answer_part)

Citation

@misc{zagribelnyy2026singleanswerenoughrethinking,
      title={When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs}, 
      author={Bogdan Zagribelnyy and Ivan Ilin and Maksim Kuznetsov and Nikita Bondarev and Roman Schutski
                and Thomas MacDougall and Rim Shayakhmetov and Zulfat Miftakhutdinov
                and Mikolaj Mizera and Vladimir Aladinskiy and Alex Aliper and Alex Zhavoronkov},
      year={2026},
      eprint={2602.03554},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2602.03554}, 
}