🧠

Model

Molcrawl Compounds Bert Small

Name: Molcrawl Compounds Bert Small
Author: Kojima Lab

by Kojima Lab hf-model--kojima-lab--molcrawl-compounds-bert-small

Free2AITools Nexus Index

39.0 Top 100%

S: Semantic 50

A: Authority 0

P: Popularity 5

R: Recency 99

Q: Quality 65

Tech Context

0.09B Params

512 Ctx

Vital Performance

56 DL / 30D

0.0%

Source →

Audited 39 FNI Score

Tiny 0.09B Params

1k Context

56 Downloads

8G GPU ~2GB Est. VRAM

Dense BERTFORMASKEDLM Architecture

Commercial APACHE License

Model Information Summary
Entity Passport
Registry ID	hf-model--kojima-lab--molcrawl-compounds-bert-small
License	Apache-2.0
Provider	huggingface

💾

Compute Threshold

~1.4GB VRAM

Interactive

Analyze Hardware

Hardware Compatibility Test

▼

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX

@misc{hf_model__kojima_lab__molcrawl_compounds_bert_small,
  author = {Kojima Lab},
  title = {Molcrawl Compounds Bert Small Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/kojima-lab/molcrawl-compounds-bert-small}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}

APA Style

Kojima Lab. (2026). Molcrawl Compounds Bert Small [Model]. Free2AITools. https://huggingface.co/kojima-lab/molcrawl-compounds-bert-small

🔬Technical Deep Dive

Full Specifications [+]

Quick Commands

🦙 Ollama Run

ollama run molcrawl-compounds-bert-small

🤗 HF Download

huggingface-cli download kojima-lab/molcrawl-compounds-bert-small

⚖️ Free2AITools Nexus Index V2.0

Methodology Index Protocol

Semantic (S) 50

Authority (A) 0

Popularity (P) 5

Recency (R) 99

Quality (Q) 65

💬 Index Insight

FNI V2.0 for Molcrawl Compounds Bert Small: Semantic (S:50), Authority (A:0), Popularity (P:5), Recency (R:99), Quality (Q:65).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit

Unbiased Data Node Refresh: VFS Live

---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Technical Deep Dive

molcrawl-compounds-bert-small

Model Description

GPT-2 small (124M parameters) foundation model pre-trained on compound SMILES strings from the MolCrawl dataset.

The tokenizer is a character-level BPE tokenizer (vocab_size=612) that encodes each SMILES character as a separate token. Input SMILES strings should be passed without spaces (e.g. CC(=O)O). The [SEP] token (id=13) is used as the end-of-sequence marker.

Datasets

MolCrawl compounds corpus (chembl + zinc + opv + reddb + pubchemqc): https://github.com/mmai-framework-lab/MolCrawl-HFuploader/blob/main/workflows/hugging_face/run_upload_hf.sh (Pre-training corpus)
Model Type: bert
Data Type: Molecule/Compound
Training Date: 2026-04-13

Usage

python

from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch

model = AutoModelForMaskedLM.from_pretrained("kojima-lab/molcrawl-compounds-bert-small")
tokenizer = AutoTokenizer.from_pretrained("kojima-lab/molcrawl-compounds-bert-small")

# Predict masked SMILES token
prompt = "CC(=O)[MASK]"
inputs = tokenizer(prompt, return_tensors="pt")
mask_token_id = tokenizer.mask_token_id
mask_index = (inputs["input_ids"] == mask_token_id).nonzero(as_tuple=True)[1]

with torch.no_grad():
    outputs = model(**inputs)
logits = outputs.logits

predicted_token_id = logits[0, mask_index].argmax(dim=-1)
predicted_token = tokenizer.decode(predicted_token_id)
result = prompt.replace("[MASK]", predicted_token)
print(f"Predicted: {result}")

Training

This model was trained with the RIKEN Foundation Model pipeline. For more details, please refer to the training configuration files included in this repository.

License

This model is released under the APACHE-2.0 license.

Citation

If you use this model, please cite:

bibtex

@misc{molcrawl_compounds_bert_small,
  title={molcrawl-compounds-bert-small},
  author={{RIKEN}},
  year={2026},
  publisher={{Hugging Face}},
  url={{https://huggingface.co/kojima-lab/molcrawl-compounds-bert-small}}
}

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

• Benchmark scores may vary based on evaluation methodology and hardware configuration.
• VRAM requirements are estimates; actual usage depends on quantization and batch size.
• FNI scores are relative rankings and may change as new models are added.
⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub

56Downloads

Hub Discussions

🤗 Data Source: Hugging Face ↗

🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-model--kojima-lab--molcrawl-compounds-bert-small
slug: kojima-lab--molcrawl-compounds-bert-small
source: huggingface
author: Kojima Lab
license: Apache-2.0
tags: safetensors, bert, pytorch, molecule-compound, fill-mask, license:apache-2.0, region:us

⚙️ Technical Specs

architecture: BertForMaskedLM
params billions: 0.09
context length: 512
pipeline tag: fill-mask
vram gb: 1.4
vram is estimated: true
vram formula: VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads: 56
stars: 0
forks: 0

Data indexed from public sources. Updated daily.