mirror of
https://github.com/zenlm/zen-coder.git
synced 2026-11-10 21:30:01 +00:00
- Rename Qwen2.5-Coder-* examples to zen-coder-* (consistent Zen branding) - Add LLM.md knowledge base (symlinked as CLAUDE.md/AGENTS.md/etc.) - Update .gitignore: exclude model weights and AI symlink files - Add training configs, inference scripts, test suite - Add MLX README, model card, Makefile for common operations
37 lines
1.3 KiB
Python
37 lines
1.3 KiB
Python
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
device = "cuda" # the device to load the model onto
|
|
|
|
# Now you do not need to add "trust_remote_code=True"
|
|
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-coder")
|
|
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-coder", device_map="auto").eval()
|
|
|
|
# tokenize the input into tokens
|
|
|
|
# Instead of using model.chat(), we directly use model.generate()
|
|
# But you need to use tokenizer.apply_chat_template() to format your inputs as shown below
|
|
prompt = "write a quick sort algorithm."
|
|
messages = [
|
|
{"role": "system", "content": "You are Zen. You are a helpful assistant."},
|
|
{"role": "user", "content": prompt}
|
|
]
|
|
text = tokenizer.apply_chat_template(
|
|
messages,
|
|
tokenize=False,
|
|
add_generation_prompt=True
|
|
)
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
|
|
|
# Directly use generate() and tokenizer.decode() to get the output.
|
|
# Use `max_new_tokens` to control the maximum output length.
|
|
generated_ids = model.generate(
|
|
model_inputs.input_ids,
|
|
max_new_tokens=2048 # can increase the output length
|
|
)
|
|
generated_ids = [
|
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
|
]
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|
|
|
print(response)
|