A Moe model built on top of Qwen1.5-7B-Chat, Qwen1.5-7B and Crystalcareai/CrystalQwen-1.5-7B.

```
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "mzbac/qwen-1.5-2x3-hf"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    load_in_4bit=True,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_id)

chat = [
    {"role": "user", "content": "how backpropagation works?"},
    {"role": "assistant", "content": "\n"},
]

text = tokenizer.apply_chat_template(chat, tokenize=False)

inputs = tokenizer.encode(text, return_tensors="pt").to("cuda")

generate_kwargs = dict(
    input_ids=inputs,
    temperature=0.6,
    max_new_tokens=500,
    do_sample=True,
)

outputs = model.generate(**generate_kwargs)
print(tokenizer.decode(outputs[0]))
```