GLM-4.6-quantized.w4a16

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/GLM-4.6-quantized.w4a16"
number_gpus = 4

sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.utils import dispatch_for_generation

MODEL_ID = "zai-org/GLM-4.6"

# Load model.
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

# Select calibration dataset.
DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"

# Select number of samples.
# Increasing the number of samples can improve accuracy.
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
ds = ds.shuffle(seed=42)

def preprocess(example):
    return {
        "text": tokenizer.apply_chat_template(
            example["messages"],
            tokenize=False,
        )
    }

ds = ds.map(preprocess)

# Tokenize inputs.
def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
        add_special_tokens=False,
    )

ds = ds.map(tokenize, remove_columns=ds.column_names)

# Configure the quantization algorithm and scheme with explicit parameters.
recipe = GPTQModifier(
    targets="Linear",
    scheme="W4A16",
    ignore=[
        "lm_head",
        "re:.*mlp.gate$"
    ],
)

# Apply quantization.
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    pipeline="sequential",
    sequential_targets=["Glm4MoeDecoderLayer"],  
    trust_remote_code_model=True,
)

SAVE_DIR = "./" + MODEL_ID.rstrip("/").split("/")[-1] + "-quantized.w4a16"
model.save_pretrained(SAVE_DIR, save_compressed=True)
tokenizer.save_pretrained(SAVE_DIR)

lm_eval --model local-chat-completions \
  --tasks mmlu_pro  \
  --model_args "model=RedHatAI/GLM-4.6-quantized.w4a16,max_length=90000,base_url=http://0.0.0.0:3758/v1/chat/completions,num_concurrent=128,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \
  --num_fewshot 5 \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --output_path ./ \
  --seed 42 \
  --gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,max_gen_toks=64000"


lm_eval --model local-chat-completions \
  --tasks leaderboard_ifeval  \
  --model_args "model=RedHatAI/GLM-4.6-quantized.w4a16,max_length=90000,base_url=http://0.0.0.0:3758/v1/chat/completions,num_concurrent=128,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \
  --num_fewshot 5 \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --output_path ./ \
  --seed 42 \
  --gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,max_gen_toks=64000"