GLM-4.7-int4-mixed-AutoRound

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
from auto_round import AutoRound
from auto_round.utils import llm_load_model

model_name = "zai-org/GLM-4.7"
model, tokenizer = llm_load_model(model_name, device="cpu")

layer_config = {}
for n, m in model.named_modules():
    if isinstance(m, torch.nn.Linear):
        if "expert" in n and "shared_experts" not in n:
            layer_config[n] = {"bits": 4}
            print(n, 4)
        elif n != "lm_head":
            layer_config[n] = {"bits": 8}
            print(n, 8)

autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, disable_opt_rtn=True)
autoround.quantize_and_save(format="auto_round", output_dir="tmp_autoround")