Meta-Llama-3.1-8B-Instruct-quantized.w4a16

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Meta-Llama-3.1-8B-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)

podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \
 --ipc=host \
--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
--env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \
--name=vllm \
registry.access.redhat.com/rhaiis/rh-vllm-cuda \
vllm serve \
--tensor-parallel-size 8 \
--max-model-len 32768  \
--enforce-eager --model RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16

# Download model from Red Hat Registry via docker
# Note: This downloads the model to ~/.cache/instructlab/models unless --model-dir is specified.
ilab model download --repository docker://registry.redhat.io/rhelai1/llama-3-1-8b-instruct-quantized-w4a16:1.5

# Serve model via ilab
ilab model serve --model-path ~/.cache/instructlab/models/llama-3-1-8b-instruct-quantized-w4a16
  
# Chat with model
ilab model chat --model ~/.cache/instructlab/models/llama-3-1-8b-instruct-quantized-w4a16

# Attach model to vllm server. This is an NVIDIA template
# Save as: inferenceservice.yaml
apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  annotations:
    openshift.io/display-name: llama-3-1-8b-instruct-quantized-w4a16 # OPTIONAL CHANGE
    serving.kserve.io/deploymentMode: RawDeployment
  name: llama-3-1-8b-instruct-quantized-w4a16          # specify model name. This value will be used to invoke the model in the payload
  labels:
    opendatahub.io/dashboard: 'true'
spec:
  predictor:
    maxReplicas: 1
    minReplicas: 1
    model:
      modelFormat:
        name: vLLM
      name: ''
      resources:
        limits:
          cpu: '2'			# this is model specific
          memory: 8Gi		# this is model specific
          nvidia.com/gpu: '1'	# this is accelerator specific
        requests:			# same comment for this block
          cpu: '1'
          memory: 4Gi
          nvidia.com/gpu: '1'
      runtime: vllm-cuda-runtime	# must match the ServingRuntime name above
      storageUri: oci://registry.redhat.io/rhelai1/modelcar-llama-3-1-8b-instruct-quantized-w4a16:1.5
    tolerations:
    - effect: NoSchedule
      key: nvidia.com/gpu
      operator: Exists

# make sure first to be in the project where you want to deploy the model
# oc project <project-name>

# apply both resources to run model

# Apply the ServingRuntime
oc apply -f vllm-servingruntime.yaml

# Apply the InferenceService
oc apply -f qwen-inferenceservice.yaml

# Replace <inference-service-name> and <cluster-ingress-domain> below:
# - Run `oc get inferenceservice` to find your URL if unsure.

# Call the server using curl:
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
        -H "Content-Type: application/json" \
        -d '{
    "model": "llama-3-1-8b-instruct-quantized-w4a16",
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "max_tokens": 1,
    "messages": [
        {
            "role": "user",
            "content": "How can a bee fly when its wings are so small?"
        }
    ]
}'

from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from datasets import load_dataset

model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"

num_samples = 756
max_seq_len = 4064

tokenizer = AutoTokenizer.from_pretrained(model_id)

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

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

examples = [tokenizer(example["text"], padding=False, max_length=max_seq_len, truncation=True) for example in ds]
    
quantize_config = BaseQuantizeConfig(
  bits=4,
  group_size=128,
  desc_act=True,
  model_file_base_name="model",
  damp_percent=0.1,
)

model = AutoGPTQForCausalLM.from_pretrained(
  model_id,
  quantize_config,
  device_map="auto",
)

model.quantize(examples)
model.save_pretrained("Meta-Llama-3.1-8B-Instruct-quantized.w4a16")

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Meta-Llama-3.1-8B-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 RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

python3 evalplus/sanitize.py \
  humaneval/neuralmagic--Meta-Llama-3.1-8B-Instruct-quantized.w4a16_vllm_temp_0.2

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/neuralmagic--Meta-Llama-3.1-8B-Instruct-quantized.w4a16_vllm_temp_0.2-sanitized