pip install hanzoai

from hanzoai import Hanzo

client = Hanzo(api_key="hk-your-api-key")

response = client.chat.completions.create(
    model="zen4",
    messages=[{"role": "user", "content": "Hello, Zen!"}],
)
print(response.choices[0].message.content)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zenlm/zen-coder-flash"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [{"role": "user", "content": "Write a Python function for binary search"}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(inputs.to(model.device), max_new_tokens=512, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

vllm serve zenlm/zen-coder-flash \
    --tensor-parallel-size 4 \
    --enable-auto-tool-choice

python -m sglang.launch_server \
    --model-path zenlm/zen-coder-flash \
    --tp-size 4 \
    --speculative-algorithm EAGLE

from mlx_lm import load, generate

model, tokenizer = load("zenlm/zen-coder-flash")
response = generate(model, tokenizer, prompt="Write a Rust function for quicksort", max_tokens=256)
print(response)