Instructions to use trillionlabs/TxGravity-30B-A5B-Open with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trillionlabs/TxGravity-30B-A5B-Open with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="trillionlabs/TxGravity-30B-A5B-Open")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trillionlabs/TxGravity-30B-A5B-Open")
model = AutoModelForCausalLM.from_pretrained("trillionlabs/TxGravity-30B-A5B-Open", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trillionlabs/TxGravity-30B-A5B-Open with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trillionlabs/TxGravity-30B-A5B-Open"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trillionlabs/TxGravity-30B-A5B-Open",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trillionlabs/TxGravity-30B-A5B-Open

SGLang

How to use trillionlabs/TxGravity-30B-A5B-Open with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "trillionlabs/TxGravity-30B-A5B-Open" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trillionlabs/TxGravity-30B-A5B-Open",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "trillionlabs/TxGravity-30B-A5B-Open" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trillionlabs/TxGravity-30B-A5B-Open",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trillionlabs/TxGravity-30B-A5B-Open with Docker Model Runner:
```
docker model run hf.co/trillionlabs/TxGravity-30B-A5B-Open
```

TxGravity-30B-A5B-Open / README.md

sungjunhan-trl

Update README.md

e2c7df7 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

9.47 kB

	---
	license: apache-2.0
	language:
	- en
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- moe
	- mixture-of-experts
	- gravity
	- txgravity
	- therapeutics
	- tdc
	- trillion-labs
	base_model:
	- trillionlabs/Gravity-30B-A5B
	---

	# TxGravity-30B-A6B-Open

	## Model Summary

	TxGravity-30B-A6B-Open is a therapeutics-focused, task-specialized model built on the Gravity-30B-A5B base. It predicts a broad range of therapeutic properties — small-molecule ADMET, toxicity, drug–target interaction, protein–protein and peptide–MHC interaction, and more — by converting the Therapeutic Data Commons (TDC) benchmark tasks into an instruction format for LLMs, in the same spirit as Google's TxGemma.

	TxGravity is co-developed by SK Biopharmaceuticals (SKBP) and Trillion Labs.

	It is trained on TDC tasks reformatted as single-turn instructions (instruction → answer), covering 57 tasks. Answers are formatted as `(A)`/`(B)` for binary classification or a normalized `000`–`1000` bin for regression.

	This release is the open-license version, with any datasets restricted to non-commercial use excluded from training.

	\| Property \| Value \|
	\|---\|---\|
	\| Total Parameters \| 29.56B \|
	\| Active Parameters \| ~6B \|
	\| Architecture \| GravityMoE (DeepSeek-V3-compatible) \|
	\| Layers \| 52 \|
	\| Routed / Shared Experts \| 64 (top-8) / 1 \|
	\| Context Length \| 8,192 tokens \|
	\| Precision \| bf16 \|
	\| Base model \| Gravity-30B-A5B \|

	> ⚠️ This is a task-specialized property predictor, not a general instruction-tuned or safety-aligned assistant. Its outputs are intended for the TDC-style therapeutic prediction prompts it was trained on. Predictions may be inaccurate, biased, or incomplete and must be independently verified before any experimental, clinical, or decision-making use.

	## Performance

	Evaluated on the TDC therapeutic benchmark against a reproduced TxGemma-27B baseline. Over 60 comparable tasks: 16 wins / 26 ties / 18 losses (6 tasks excluded for lack of a paper-reported comparison). A win/loss requires the margin to exceed the tie threshold; otherwise the task is scored a tie.

	Wins (16 tasks) — TxGravity beats TxGemma-27B on: `bindingdb_ki`, `bindingdb_ic50`, `protein_sabdab`, `ppbr_az`, `caco2_wang`, `lipophilicity_astrazeneca`, `half_life_obach`, `clearance_hepatocyte_az`, `ld50_zhu`, `bioavailability_ma`, `buchwald_hartwig`, `drugcomb_css`, `drugcomb_loewe`, `drugcomb_zip`, `drugcomb_hsa`, `drugcomb_bliss` — spanning binding affinity, ADMET, toxicity, and drug-combination synergy.

	Highlights: `bindingdb_ki` PCC 0.750 vs -0.112, `bindingdb_ic50` Spearman 0.766 vs 0.643, `protein_sabdab` MAE 0.969 vs 2.332, `ld50_zhu` MAE 0.651 vs 0.776.

	### Full results

	Margin is TxGravity - TxGemma, in percentage points (%p) for score metrics or relative percent (%rel) for error metrics (MAE/MSE, lower is better). Up-arrow = higher is better, down-arrow = lower is better.

	\| Task \| Metric \| N \| TxGravity \| TxGemma-27B \| Margin \| Verdict \|
	\|---\|---\|---\|---\|---\|---\|---\|
	\| bindingdb_ic50 \| Spearman ↑ \| 35725 \| 0.7660 \| 0.6430 \| +12.3%p \| WIN \|
	\| bindingdb_ki \| PCC ↑ \| 11857 \| 0.7500 \| -0.1120 \| +86.2%p \| WIN \|
	\| bioavailability_ma \| AUROC ↑ \| 128 \| 0.7490 \| 0.6970 \| +5.2%p \| WIN \|
	\| buchwald_hartwig \| PCC ↑ \| 791 \| 0.8920 \| 0.8550 \| +3.7%p \| WIN \|
	\| caco2_wang \| MAE ↓ \| 182 \| 0.4160 \| 0.4660 \| +10.7%rel \| WIN \|
	\| clearance_hepatocyte_az \| Spearman ↑ \| 243 \| 0.3240 \| 0.2910 \| +3.3%p \| WIN \|
	\| drugcomb_bliss \| MAE ↓ \| 59708 \| 3.7370 \| 3.9280 \| +4.9%rel \| WIN \|
	\| drugcomb_css \| MAE ↓ \| 59708 \| 7.8380 \| 9.4180 \| +16.8%rel \| WIN \|
	\| drugcomb_hsa \| MAE ↓ \| 59708 \| 3.5840 \| 3.7880 \| +5.4%rel \| WIN \|
	\| drugcomb_loewe \| MAE ↓ \| 59708 \| 6.4130 \| 7.6720 \| +16.4%rel \| WIN \|
	\| drugcomb_zip \| MAE ↓ \| 59708 \| 3.0610 \| 3.4100 \| +10.2%rel \| WIN \|
	\| half_life_obach \| Spearman ↑ \| 135 \| 0.3600 \| 0.2890 \| +7.1%p \| WIN \|
	\| ld50_zhu \| MAE ↓ \| 1478 \| 0.6510 \| 0.7760 \| +16.1%rel \| WIN \|
	\| lipophilicity_astrazeneca \| MAE ↓ \| 840 \| 0.5700 \| 0.5950 \| +4.2%rel \| WIN \|
	\| ppbr_az \| MAE ↓ \| 559 \| 8.2900 \| 9.4180 \| +12.0%rel \| WIN \|
	\| protein_sabdab \| MAE ↓ \| 99 \| 0.9690 \| 2.3320 \| +58.4%rel \| WIN \|
	\| ames \| AUROC ↑ \| 1457 \| 0.8410 \| 0.8300 \| +1.1%p \| TIE \|
	\| bbb_martins \| AUROC ↑ \| 406 \| 0.9190 \| 0.8970 \| +2.2%p \| TIE \|
	\| bindingdb_patent \| PCC ↑ \| 49028 \| 0.5410 \| 0.5140 \| +2.7%p \| TIE \|
	\| carcinogens_lagunin \| Accuracy ↑ \| 56 \| 0.8750 \| 0.8930 \| -1.8%p \| TIE \|
	\| clearance_microsome_az \| Spearman ↑ \| 221 \| 0.5000 \| 0.4870 \| +1.3%p \| TIE \|
	\| clintox \| AUROC ↑ \| 297 \| 0.7610 \| 0.7560 \| +0.5%p \| TIE \|
	\| cyp1a2_veith \| AUPRC ↑ \| 2517 \| 0.9310 \| 0.9350 \| -0.4%p \| TIE \|
	\| cyp2c19_veith \| AUROC ↑ \| 2534 \| 0.8940 \| 0.8910 \| +0.3%p \| TIE \|
	\| cyp2c9_veith \| AUPRC ↑ \| 2419 \| 0.7920 \| 0.7820 \| +1.0%p \| TIE \|
	\| cyp2d6_veith \| AUPRC ↑ \| 2626 \| 0.6840 \| 0.6620 \| +2.2%p \| TIE \|
	\| cyp3a4_veith \| AUPRC ↑ \| 2467 \| 0.8610 \| 0.8410 \| +2.0%p \| TIE \|
	\| dili \| AUROC ↑ \| 96 \| 0.8930 \| 0.8890 \| +0.4%p \| TIE \|
	\| herg \| AUROC ↑ \| 132 \| 0.8930 \| 0.9000 \| -0.7%p \| TIE \|
	\| herg_central \| AUROC ↑ \| 61379 \| 0.8760 \| 0.8830 \| -0.7%p \| TIE \|
	\| herg_karim \| Accuracy ↑ \| 2690 \| 0.7920 \| 0.8000 \| -0.8%p \| TIE \|
	\| hia_hou \| AUROC ↑ \| 117 \| 0.9860 \| 0.9860 \| +0.0%p \| TIE \|
	\| hiv \| AUROC ↑ \| 8227 \| 0.7640 \| 0.7930 \| -2.9%p \| TIE \|
	\| huri \| AUPRC ↑ \| 4204 \| 0.8080 \| 0.7920 \| +1.6%p \| TIE \|
	\| mhc2_iedb_jensen \| AUROC ↑ \| 26856 \| 0.8680 \| 0.8500 \| +1.8%p \| TIE \|
	\| pgp_broccatelli \| AUROC ↑ \| 245 \| 0.9380 \| 0.9320 \| +0.6%p \| TIE \|
	\| sarscov2_3clpro_diamond \| AUROC ↑ \| 176 \| 0.7470 \| 0.7250 \| +2.2%p \| TIE \|
	\| skin_reaction \| AUROC ↑ \| 82 \| 0.6510 \| 0.6370 \| +1.4%p \| TIE \|
	\| tox21 \| AUROC ↑ \| 15600 \| 0.8230 \| 0.8430 \| -2.0%p \| TIE \|
	\| toxcast \| AUROC ↑ \| 307282 \| 0.8970 \| 0.9050 \| -0.8%p \| TIE \|
	\| vdss_lombardo \| Spearman ↑ \| 226 \| 0.5820 \| 0.5660 \| +1.6%p \| TIE \|
	\| weber \| AUROC ↑ \| 9417 \| 0.7180 \| 0.7390 \| -2.1%p \| TIE \|
	\| bindingdb_kd \| PCC ↑ \| 1630 \| 0.5220 \| 0.5960 \| -7.4%p \| LOSS \|
	\| butkiewicz \| AUROC ↑ \| 401997 \| 0.7540 \| 0.8620 \| -10.8%p \| LOSS \|
	\| cyp2c9_substrate_carbonmangels \| AUPRC ↑ \| 135 \| 0.3460 \| 0.4730 \| -12.7%p \| LOSS \|
	\| cyp2d6_substrate_carbonmangels \| AUPRC ↑ \| 135 \| 0.7080 \| 0.7380 \| -3.0%p \| LOSS \|
	\| cyp3a4_substrate_carbonmangels \| AUROC ↑ \| 135 \| 0.6410 \| 0.6950 \| -5.4%p \| LOSS \|
	\| davis \| MSE ↓ \| 1064 \| 0.7600 \| 0.6430 \| -18.2%rel \| LOSS \|
	\| disgenet \| MAE \| 10495 \| — \| — \| — \| excluded \|
	\| gdsc1 \| PCC \| 35462 \| — \| — \| — \| excluded \|
	\| gdsc2 \| PCC \| 18541 \| — \| — \| — \| excluded \|
	\| kiba \| MSE ↓ \| 4537 \| 0.6370 \| 0.4600 \| -38.5%rel \| LOSS \|
	\| leenay \| Spearman ↑ \| 1520 \| 0.1510 \| 0.2260 \| -7.5%p \| LOSS \|
	\| mhc1_iedb_imgt_nielsen \| AUROC ↑ \| 37197 \| 0.9200 \| 0.9680 \| -4.8%p \| LOSS \|
	\| mirtarbase \| Accuracy ↑ \| 160033 \| 0.5550 \| 0.8040 \| -24.9%p \| LOSS \|
	\| oncopolypharmacology \| PCC ↑ \| 4647 \| 0.5050 \| 0.5690 \| -6.4%p \| LOSS \|
	\| pampa_ncats \| AUROC ↑ \| 408 \| 0.6630 \| 0.7080 \| -4.5%p \| LOSS \|
	\| phase1 \| AUROC \| 561 \| — \| — \| — \| excluded \|
	\| phase2 \| AUROC \| 1279 \| — \| — \| — \| excluded \|
	\| phase3 \| AUROC \| 1200 \| — \| — \| — \| excluded \|
	\| sabdab_chen \| AUPRC ↑ \| 482 \| 0.6580 \| 0.7080 \| -5.0%p \| LOSS \|
	\| sarscov2_vitro_touret \| AUROC ↑ \| 298 \| 0.4580 \| 0.5300 \| -7.2%p \| LOSS \|
	\| solubility_aqsoldb \| MAE ↓ \| 1997 \| 0.8550 \| 0.8050 \| -6.2%rel \| LOSS \|
	\| tap \| MAE ↓ \| 240 \| 5.4400 \| 4.7850 \| -13.7%rel \| LOSS \|
	\| uspto \| Accuracy ↑ \| 221648 \| 0.0000 \| 0.0880 \| -8.8%p \| LOSS \|
	\| uspto_yields \| PCC ↑ \| 170728 \| -0.0571 \| 0.1860 \| -24.3%p \| LOSS \|

	Also included in this repo as [`summary.csv`](./summary.csv).

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("trillionlabs/TxGravity-30B-A6B-Open")
	model = AutoModelForCausalLM.from_pretrained(
	"trillionlabs/TxGravity-30B-A6B-Open", dtype="bfloat16", device_map="auto")

	messages = [{"role": "user", "content": "<TDC-formatted instruction here>"}]
	ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
	out = model.generate(ids, max_new_tokens=16)
	print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
	```

	The model expects TDC-style prompts and answers in TDC format: `(A)`/`(B)` for classification, or a `000`–`1000` normalized bin for regression.

	## License
	Apache 2.0

	## Citation

	```bibtex
	@misc{txgravity2026,
	title = {TxGravity-30B-A6B-Open},
	author = {SK Biopharmaceuticals and Trillion Labs},
	year = {2026},
	howpublished = {\url{https://huggingface.co/trillionlabs/TxGravity-30B-A6B-Open}}
	}
	```

	This model builds on the Therapeutic Data Commons (TDC) benchmark:

	```bibtex
	@article{huang2021therapeutics,
	title = {Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development},
	author = {Huang, Kexin and Fu, Tianfan and Gao, Wenhao and Zhao, Yue and Roohani, Yusuf and Leskovec, Jure and Coley, Connor W and Xiao, Cao and Sun, Jimeng and Zitnik, Marinka},
	journal = {Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks},
	year = {2021}
	}
	```

	---
	license: apache-2.0
	language:
	- en
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- moe
	- mixture-of-experts
	- gravity
	- txgravity
	- therapeutics
	- tdc
	- trillion-labs
	base_model:
	- trillionlabs/Gravity-30B-A5B
	---

	# TxGravity-30B-A6B-Open

	## Model Summary

	TxGravity-30B-A6B-Open is a therapeutics-focused, task-specialized model built on the Gravity-30B-A5B base. It predicts a broad range of therapeutic properties — small-molecule ADMET, toxicity, drug–target interaction, protein–protein and peptide–MHC interaction, and more — by converting the Therapeutic Data Commons (TDC) benchmark tasks into an instruction format for LLMs, in the same spirit as Google's TxGemma.

	TxGravity is co-developed by SK Biopharmaceuticals (SKBP) and Trillion Labs.

	It is trained on TDC tasks reformatted as single-turn instructions (instruction → answer), covering 57 tasks. Answers are formatted as `(A)`/`(B)` for binary classification or a normalized `000`–`1000` bin for regression.

	This release is the open-license version, with any datasets restricted to non-commercial use excluded from training.

	\| Property \| Value \|
	\|---\|---\|
	\| Total Parameters \| 29.56B \|
	\| Active Parameters \| ~6B \|
	\| Architecture \| GravityMoE (DeepSeek-V3-compatible) \|
	\| Layers \| 52 \|
	\| Routed / Shared Experts \| 64 (top-8) / 1 \|
	\| Context Length \| 8,192 tokens \|
	\| Precision \| bf16 \|
	\| Base model \| Gravity-30B-A5B \|

	> ⚠️ This is a task-specialized property predictor, not a general instruction-tuned or safety-aligned assistant. Its outputs are intended for the TDC-style therapeutic prediction prompts it was trained on. Predictions may be inaccurate, biased, or incomplete and must be independently verified before any experimental, clinical, or decision-making use.

	## Performance

	Evaluated on the TDC therapeutic benchmark against a reproduced TxGemma-27B baseline. Over 60 comparable tasks: 16 wins / 26 ties / 18 losses (6 tasks excluded for lack of a paper-reported comparison). A win/loss requires the margin to exceed the tie threshold; otherwise the task is scored a tie.

	Wins (16 tasks) — TxGravity beats TxGemma-27B on: `bindingdb_ki`, `bindingdb_ic50`, `protein_sabdab`, `ppbr_az`, `caco2_wang`, `lipophilicity_astrazeneca`, `half_life_obach`, `clearance_hepatocyte_az`, `ld50_zhu`, `bioavailability_ma`, `buchwald_hartwig`, `drugcomb_css`, `drugcomb_loewe`, `drugcomb_zip`, `drugcomb_hsa`, `drugcomb_bliss` — spanning binding affinity, ADMET, toxicity, and drug-combination synergy.

	Highlights: `bindingdb_ki` PCC 0.750 vs -0.112, `bindingdb_ic50` Spearman 0.766 vs 0.643, `protein_sabdab` MAE 0.969 vs 2.332, `ld50_zhu` MAE 0.651 vs 0.776.

	### Full results

	Margin is TxGravity - TxGemma, in percentage points (%p) for score metrics or relative percent (%rel) for error metrics (MAE/MSE, lower is better). Up-arrow = higher is better, down-arrow = lower is better.

	\| Task \| Metric \| N \| TxGravity \| TxGemma-27B \| Margin \| Verdict \|
	\|---\|---\|---\|---\|---\|---\|---\|
	\| bindingdb_ic50 \| Spearman ↑ \| 35725 \| 0.7660 \| 0.6430 \| +12.3%p \| WIN \|
	\| bindingdb_ki \| PCC ↑ \| 11857 \| 0.7500 \| -0.1120 \| +86.2%p \| WIN \|
	\| bioavailability_ma \| AUROC ↑ \| 128 \| 0.7490 \| 0.6970 \| +5.2%p \| WIN \|
	\| buchwald_hartwig \| PCC ↑ \| 791 \| 0.8920 \| 0.8550 \| +3.7%p \| WIN \|
	\| caco2_wang \| MAE ↓ \| 182 \| 0.4160 \| 0.4660 \| +10.7%rel \| WIN \|
	\| clearance_hepatocyte_az \| Spearman ↑ \| 243 \| 0.3240 \| 0.2910 \| +3.3%p \| WIN \|
	\| drugcomb_bliss \| MAE ↓ \| 59708 \| 3.7370 \| 3.9280 \| +4.9%rel \| WIN \|
	\| drugcomb_css \| MAE ↓ \| 59708 \| 7.8380 \| 9.4180 \| +16.8%rel \| WIN \|
	\| drugcomb_hsa \| MAE ↓ \| 59708 \| 3.5840 \| 3.7880 \| +5.4%rel \| WIN \|
	\| drugcomb_loewe \| MAE ↓ \| 59708 \| 6.4130 \| 7.6720 \| +16.4%rel \| WIN \|
	\| drugcomb_zip \| MAE ↓ \| 59708 \| 3.0610 \| 3.4100 \| +10.2%rel \| WIN \|
	\| half_life_obach \| Spearman ↑ \| 135 \| 0.3600 \| 0.2890 \| +7.1%p \| WIN \|
	\| ld50_zhu \| MAE ↓ \| 1478 \| 0.6510 \| 0.7760 \| +16.1%rel \| WIN \|
	\| lipophilicity_astrazeneca \| MAE ↓ \| 840 \| 0.5700 \| 0.5950 \| +4.2%rel \| WIN \|
	\| ppbr_az \| MAE ↓ \| 559 \| 8.2900 \| 9.4180 \| +12.0%rel \| WIN \|
	\| protein_sabdab \| MAE ↓ \| 99 \| 0.9690 \| 2.3320 \| +58.4%rel \| WIN \|
	\| ames \| AUROC ↑ \| 1457 \| 0.8410 \| 0.8300 \| +1.1%p \| TIE \|
	\| bbb_martins \| AUROC ↑ \| 406 \| 0.9190 \| 0.8970 \| +2.2%p \| TIE \|
	\| bindingdb_patent \| PCC ↑ \| 49028 \| 0.5410 \| 0.5140 \| +2.7%p \| TIE \|
	\| carcinogens_lagunin \| Accuracy ↑ \| 56 \| 0.8750 \| 0.8930 \| -1.8%p \| TIE \|
	\| clearance_microsome_az \| Spearman ↑ \| 221 \| 0.5000 \| 0.4870 \| +1.3%p \| TIE \|
	\| clintox \| AUROC ↑ \| 297 \| 0.7610 \| 0.7560 \| +0.5%p \| TIE \|
	\| cyp1a2_veith \| AUPRC ↑ \| 2517 \| 0.9310 \| 0.9350 \| -0.4%p \| TIE \|
	\| cyp2c19_veith \| AUROC ↑ \| 2534 \| 0.8940 \| 0.8910 \| +0.3%p \| TIE \|
	\| cyp2c9_veith \| AUPRC ↑ \| 2419 \| 0.7920 \| 0.7820 \| +1.0%p \| TIE \|
	\| cyp2d6_veith \| AUPRC ↑ \| 2626 \| 0.6840 \| 0.6620 \| +2.2%p \| TIE \|
	\| cyp3a4_veith \| AUPRC ↑ \| 2467 \| 0.8610 \| 0.8410 \| +2.0%p \| TIE \|
	\| dili \| AUROC ↑ \| 96 \| 0.8930 \| 0.8890 \| +0.4%p \| TIE \|
	\| herg \| AUROC ↑ \| 132 \| 0.8930 \| 0.9000 \| -0.7%p \| TIE \|
	\| herg_central \| AUROC ↑ \| 61379 \| 0.8760 \| 0.8830 \| -0.7%p \| TIE \|
	\| herg_karim \| Accuracy ↑ \| 2690 \| 0.7920 \| 0.8000 \| -0.8%p \| TIE \|
	\| hia_hou \| AUROC ↑ \| 117 \| 0.9860 \| 0.9860 \| +0.0%p \| TIE \|
	\| hiv \| AUROC ↑ \| 8227 \| 0.7640 \| 0.7930 \| -2.9%p \| TIE \|
	\| huri \| AUPRC ↑ \| 4204 \| 0.8080 \| 0.7920 \| +1.6%p \| TIE \|
	\| mhc2_iedb_jensen \| AUROC ↑ \| 26856 \| 0.8680 \| 0.8500 \| +1.8%p \| TIE \|
	\| pgp_broccatelli \| AUROC ↑ \| 245 \| 0.9380 \| 0.9320 \| +0.6%p \| TIE \|
	\| sarscov2_3clpro_diamond \| AUROC ↑ \| 176 \| 0.7470 \| 0.7250 \| +2.2%p \| TIE \|
	\| skin_reaction \| AUROC ↑ \| 82 \| 0.6510 \| 0.6370 \| +1.4%p \| TIE \|
	\| tox21 \| AUROC ↑ \| 15600 \| 0.8230 \| 0.8430 \| -2.0%p \| TIE \|
	\| toxcast \| AUROC ↑ \| 307282 \| 0.8970 \| 0.9050 \| -0.8%p \| TIE \|
	\| vdss_lombardo \| Spearman ↑ \| 226 \| 0.5820 \| 0.5660 \| +1.6%p \| TIE \|
	\| weber \| AUROC ↑ \| 9417 \| 0.7180 \| 0.7390 \| -2.1%p \| TIE \|
	\| bindingdb_kd \| PCC ↑ \| 1630 \| 0.5220 \| 0.5960 \| -7.4%p \| LOSS \|
	\| butkiewicz \| AUROC ↑ \| 401997 \| 0.7540 \| 0.8620 \| -10.8%p \| LOSS \|
	\| cyp2c9_substrate_carbonmangels \| AUPRC ↑ \| 135 \| 0.3460 \| 0.4730 \| -12.7%p \| LOSS \|
	\| cyp2d6_substrate_carbonmangels \| AUPRC ↑ \| 135 \| 0.7080 \| 0.7380 \| -3.0%p \| LOSS \|
	\| cyp3a4_substrate_carbonmangels \| AUROC ↑ \| 135 \| 0.6410 \| 0.6950 \| -5.4%p \| LOSS \|
	\| davis \| MSE ↓ \| 1064 \| 0.7600 \| 0.6430 \| -18.2%rel \| LOSS \|
	\| disgenet \| MAE \| 10495 \| — \| — \| — \| excluded \|
	\| gdsc1 \| PCC \| 35462 \| — \| — \| — \| excluded \|
	\| gdsc2 \| PCC \| 18541 \| — \| — \| — \| excluded \|
	\| kiba \| MSE ↓ \| 4537 \| 0.6370 \| 0.4600 \| -38.5%rel \| LOSS \|
	\| leenay \| Spearman ↑ \| 1520 \| 0.1510 \| 0.2260 \| -7.5%p \| LOSS \|
	\| mhc1_iedb_imgt_nielsen \| AUROC ↑ \| 37197 \| 0.9200 \| 0.9680 \| -4.8%p \| LOSS \|
	\| mirtarbase \| Accuracy ↑ \| 160033 \| 0.5550 \| 0.8040 \| -24.9%p \| LOSS \|
	\| oncopolypharmacology \| PCC ↑ \| 4647 \| 0.5050 \| 0.5690 \| -6.4%p \| LOSS \|
	\| pampa_ncats \| AUROC ↑ \| 408 \| 0.6630 \| 0.7080 \| -4.5%p \| LOSS \|
	\| phase1 \| AUROC \| 561 \| — \| — \| — \| excluded \|
	\| phase2 \| AUROC \| 1279 \| — \| — \| — \| excluded \|
	\| phase3 \| AUROC \| 1200 \| — \| — \| — \| excluded \|
	\| sabdab_chen \| AUPRC ↑ \| 482 \| 0.6580 \| 0.7080 \| -5.0%p \| LOSS \|
	\| sarscov2_vitro_touret \| AUROC ↑ \| 298 \| 0.4580 \| 0.5300 \| -7.2%p \| LOSS \|
	\| solubility_aqsoldb \| MAE ↓ \| 1997 \| 0.8550 \| 0.8050 \| -6.2%rel \| LOSS \|
	\| tap \| MAE ↓ \| 240 \| 5.4400 \| 4.7850 \| -13.7%rel \| LOSS \|
	\| uspto \| Accuracy ↑ \| 221648 \| 0.0000 \| 0.0880 \| -8.8%p \| LOSS \|
	\| uspto_yields \| PCC ↑ \| 170728 \| -0.0571 \| 0.1860 \| -24.3%p \| LOSS \|

	Also included in this repo as [`summary.csv`](./summary.csv).

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("trillionlabs/TxGravity-30B-A6B-Open")
	model = AutoModelForCausalLM.from_pretrained(
	"trillionlabs/TxGravity-30B-A6B-Open", dtype="bfloat16", device_map="auto")

	messages = [{"role": "user", "content": "<TDC-formatted instruction here>"}]
	ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
	out = model.generate(ids, max_new_tokens=16)
	print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
	```

	The model expects TDC-style prompts and answers in TDC format: `(A)`/`(B)` for classification, or a `000`–`1000` normalized bin for regression.

	## License
	Apache 2.0

	## Citation

	```bibtex
	@misc{txgravity2026,
	title = {TxGravity-30B-A6B-Open},
	author = {SK Biopharmaceuticals and Trillion Labs},
	year = {2026},
	howpublished = {\url{https://huggingface.co/trillionlabs/TxGravity-30B-A6B-Open}}
	}
	```

	This model builds on the Therapeutic Data Commons (TDC) benchmark:

	```bibtex
	@article{huang2021therapeutics,
	title = {Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development},
	author = {Huang, Kexin and Fu, Tianfan and Gao, Wenhao and Zhao, Yue and Roohani, Yusuf and Leskovec, Jure and Coley, Connor W and Xiao, Cao and Sun, Jimeng and Zitnik, Marinka},
	journal = {Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks},
	year = {2021}
	}
	```