Instructions to use summykai/Qwen3-14B-chem-dyn-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use summykai/Qwen3-14B-chem-dyn-tokenizer with Transformers:

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

pipe = pipeline("text-generation", model="summykai/Qwen3-14B-chem-dyn-tokenizer")
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("summykai/Qwen3-14B-chem-dyn-tokenizer")
model = AutoModelForCausalLM.from_pretrained("summykai/Qwen3-14B-chem-dyn-tokenizer", 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 summykai/Qwen3-14B-chem-dyn-tokenizer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "summykai/Qwen3-14B-chem-dyn-tokenizer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "summykai/Qwen3-14B-chem-dyn-tokenizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/summykai/Qwen3-14B-chem-dyn-tokenizer

SGLang

How to use summykai/Qwen3-14B-chem-dyn-tokenizer 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 "summykai/Qwen3-14B-chem-dyn-tokenizer" \
    --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": "summykai/Qwen3-14B-chem-dyn-tokenizer",
		"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 "summykai/Qwen3-14B-chem-dyn-tokenizer" \
        --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": "summykai/Qwen3-14B-chem-dyn-tokenizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use summykai/Qwen3-14B-chem-dyn-tokenizer with Docker Model Runner:
```
docker model run hf.co/summykai/Qwen3-14B-chem-dyn-tokenizer
```

Model Card for summykai/Qwen3-14B-chem-dyn-tokenizer

A Qwen3-14B model augmented with the InternS1 dynamic tokenizer for chemistry/biomolecular text. No full fine-tune was performed; we adapted tokenization and warmed the new token rows so the model is ready for downstream SFT/RL on chemistry tasks.

InternS1 tokenizer compression

Figure: Tokenization efficiency from the InternS1 technical report — SMILES/IUPAC compression ~2.64× vs ~1.44–1.51× for common LLM tokenizers.

Model Details

Developed by: Summykai
License: Apache-2.0
Finetuned from: Qwen/Qwen3-14B
Model type: QwenForCausalLM
Languages: Multilingual (inherits from Qwen3)

What changed vs. base Qwen3-14B?

Dynamic tokenizer integration (InternS1)
We ship tokenization_interns1.py and three SentencePiece models:

tokenizer_SMILES.model (SMILES/SELFIES)
tokenizer_IUPAC.model (IUPAC names)
tokenizer_FASTA.model (protein sequences)

The tokenizer auto-detects long chemistry/biomolecular spans and switches to the SP model, or you can wrap with explicit tags:

<SMILES> CC(=O)OC1=CC=CC=C1C(=O)O </SMILES>
<IUPAC> 2-acetoxybenzoic acid </IUPAC>

Logical auto-detect tokens (e.g., <SMILES_AUTO_DETECT>…</SMILES_AUTO_DETECT>) do not consume ids.

Effective vocabulary size: 152,971.

Warm-up of new rows (no full finetune):

Transformer layers frozen; trained only new embedding rows (+ matching lm_head rows if untied).
Cross-entropy objective; ~1,500 steps; ~3,986,558 token exposures.
Stability aids: fp32 CE, grad-clip=1.0, small LR.

Initialization strategy (better than random):
New rows were not left random. We projected domain embeddings into Qwen3’s space (ridge-regularized linear map) to give chemistry tokens meaningful initial locations. After merging, test_merge.py verified max |Δ| emb/head = 0.0.

How to Use

Install: RDKit is strongly recommended for high-quality SMILES auto-detection.

pip install rdkit-pypi sentencepiece transformers
# or via conda:
# conda install -c conda-forge rdkit

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "summykai/Qwen3-14B-chem-dyn-tokenizer"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, torch_dtype="auto")
prompt = "Name and SMILES for aspirin: <SMILES>CC(=O)OC1=CC=CC=C1C(=O)O</SMILES>"
out = model.generate(**tok(prompt, return_tensors="pt"), max_new_tokens=64)
print(tok.decode(out[0], skip_special_tokens=True))

Files

Model: model-*.safetensors, model.safetensors.index.json, config.json, generation_config.json
Tokenizer: vocab.json, merges.txt, tokenizer_config.json, special_tokens_map.json, tokenization_interns1.py, tokenizer_SMILES.model, tokenizer_IUPAC.model, tokenizer_FASTA.model
Figures: figures/compression_interns1.png

Acknowledgements

Intern / Shanghai AI Lab — InternS1 tokenizer and report
Qwen Team — Qwen3-14B base model

Contact

Summykai (HF & GitHub): https://github.com/Summykai

Downloads last month: 49

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for summykai/Qwen3-14B-chem-dyn-tokenizer

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(354)

this model