license, language, tags, pipeline_tag, library_name, base_model
| license | language | tags | pipeline_tag | library_name | base_model | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| apache-2.0 |
|
|
text-generation | transformers | zenlm/zen-pro |
Zen Medical
Parameters: 8B | Architecture: Zen 3 Architecture | Context: 32K | License: Apache 2.0 | Released: 2024-10-01
Medical AI for clinical research, literature synthesis, pharmacology, and diagnostic support workflows.
Designed for medical researchers and healthcare AI developers. Not for clinical diagnosis.
Base weights: zenlm/zen-pro
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-pro", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-pro")
messages = [{"role": "user", "content": "Your domain-specific prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(output[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
The Zen LM Family
Joint research between Hanzo AI (Techstars '17), Zoo Labs Foundation (501c3), and Lux Partners Limited.
All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.
HuggingFace · Chat · API · Docs