Meta-Llama-3.1-70B-Instruct-quantized.w4a16

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w4a16"
number_gpus = 1
max_model_len = 8192

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, max_model_len=max_model_len)

outputs = llm.generate(prompts, sampling_params)

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

from transformers import AutoTokenizer
from datasets import Dataset
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
import random

model_id = "meta-llama/Meta-Llama-3.1-70B-Instruct"

num_samples = 512
max_seq_len = 8192

tokenizer = AutoTokenizer.from_pretrained(model_id)

preprocess_fn = lambda example: {"text": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{text}".format_map(example)}

dataset_name = "neuralmagic/LLM_compression_calibration"
dataset = load_dataset(dataset_name, split="train")
ds = dataset.shuffle().select(range(num_samples))
ds = ds.map(preprocess_fn)

recipe = GPTQModifier(
  targets="Linear",
  scheme="W4A16",
  ignore=["lm_head"],
  dampening_frac=0.01,
)

model = SparseAutoModelForCausalLM.from_pretrained(
  model_id,
  device_map="auto",
  trust_remote_code=True,
)

oneshot(
  model=model,
  dataset=ds,
  recipe=recipe,
  max_seq_length=max_seq_len,
  num_calibration_samples=num_samples,
)
model.save_pretrained("Meta-Llama-3.1-70B-Instruct-quantized.w4a16")

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
  --tasks mmlu_llama_3.1_instruct \
  --fewshot_as_multiturn \
  --apply_chat_template \
  --num_fewshot 5 \
  --batch_size auto

python3 codegen/generate.py \
  --model neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w4a16 \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

python3 evalplus/sanitize.py \
  humaneval/neuralmagic--Meta-Llama-3.1-70B-Instruct-quantized.w4a16_vllm_temp_0.2

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/neuralmagic--Meta-Llama-3.1-70B-Instruct-quantized.w4a16_vllm_temp_0.2-sanitized