This model is a quantized version of Meta-Llama-3.1-8B-Instruct. It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model, including multiple-choice, math reasoning, and open-ended text generation. Meta-Llama-3.1-8B-Instruct-quantized.w4a16 achieves 93.0% recovery for the Arena-Hard evaluation, 98.9% for OpenLLM v1 (using Meta's prompting when available), 96.1% for OpenLLM v2, 99.7% for HumanEval pass@1, and 97.4% for HumanEval+ pass@1.
This model was obtained by quantizing the weights of Meta-Llama-3.1-8B-Instruct to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.
Only the weights of the linear operators within transformers blocks are quantized. Symmetric per-group quantization is applied, in which a linear scaling per group of 128 parameters maps the INT4 and floating point representations of the quantized weights. AutoGPTQ is used for quantization with 10% damping factor and 768 sequences taken from Neural Magic's LLM compression calibration dataset.
This model can be deployed efficiently using the vLLM backend, as shown in the example below.
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer
model_id = "neuralmagic/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)
vLLM also supports OpenAI-compatible serving. See the documentation for more details.
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
See Red Hat AI Inference Server documentation for more details.
# 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
See Red Hat Enterprise Linux AI documentation for more details.
# Setting up vllm server with ServingRuntime
# Save as: vllm-servingruntime.yaml
apiVersion: serving.kserve.io/v1alpha1
kind: ServingRuntime
metadata:
name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name
annotations:
openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe
opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]'
labels:
opendatahub.io/dashboard: 'true'
spec:
annotations:
prometheus.io/port: '8080'
prometheus.io/path: '/metrics'
multiModel: false
supportedModelFormats:
- autoSelect: true
name: vLLM
containers:
- name: kserve-container
image: quay.io/modh/vllm:rhoai-2.20-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm
command:
- python
- -m
- vllm.entrypoints.openai.api_server
args:
- "--port=8080"
- "--model=/mnt/models"
- "--served-model-name={{.Name}}"
env:
- name: HF_HOME
value: /tmp/hf_home
ports:
- containerPort: 8080
protocol: TCP
# 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?"
}
]
}'
See Red Hat Openshift AI documentation for more details.
This model was created by applying the AutoGPTQ library as presented in the code snipet below. Although AutoGPTQ was used for this particular model, Neural Magic is transitioning to using llm-compressor which supports several quantization schemes and models not supported by AutoGPTQ.
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")
This model was evaluated on the well-known Arena-Hard, OpenLLM v1, OpenLLM v2, HumanEval, and HumanEval+ benchmarks. In all cases, model outputs were generated with the vLLM engine.
Arena-Hard evaluations were conducted using the Arena-Hard-Auto repository. The model generated a single answer for each prompt form Arena-Hard, and each answer was judged twice by GPT-4. We report below the scores obtained in each judgement and the average.
OpenLLM v1 and v2 evaluations were conducted using Neural Magic's fork of lm-evaluation-harness (branch llama_3.1_instruct). This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challenge and GSM-8K that match the prompting style of Meta-Llama-3.1-Instruct-evals and a few fixes to OpenLLM v2 tasks.
HumanEval and HumanEval+ evaluations were conducted using Neural Magic's fork of the EvalPlus repository.
Detailed model outputs are available as HuggingFace datasets for Arena-Hard, OpenLLM v2, and HumanEval.
Note: Results have been updated after Meta modified the chat template.
| Category | Benchmark | Meta-Llama-3.1-8B-Instruct | Meta-Llama-3.1-8B-Instruct-quantized.w4a16 (this model) | Recovery |
| LLM as a judge | Arena Hard | 25.8 (25.1 / 26.5) | 27.2 (27.6 / 26.7) | 105.4% |
| OpenLLM v1 | MMLU (5-shot) | 68.3 | 66.9 | 97.9% |
| MMLU (CoT, 0-shot) | 72.8 | 71.1 | 97.6% | |
| ARC Challenge (0-shot) | 81.4 | 80.2 | 98.0% | |
| GSM-8K (CoT, 8-shot, strict-match) | 82.8 | 82.9 | 100.2% | |
| Hellaswag (10-shot) | 80.5 | 79.9 | 99.3% | |
| Winogrande (5-shot) | 78.1 | 78.0 | 99.9% | |
| TruthfulQA (0-shot, mc2) | 54.5 | 52.8 | 96.9% | |
| Average | 74.3 | 73.5 | 98.9% | |
| OpenLLM v2 | MMLU-Pro (5-shot) | 30.8 | 28.8 | 93.6% |
| IFEval (0-shot) | 77.9 | 76.3 | 98.0% | |
| BBH (3-shot) | 30.1 | 28.9 | 96.1% | |
| Math-lvl-5 (4-shot) | 15.7 | 14.8 | 94.4% | |
| GPQA (0-shot) | 3.7 | 4.0 | 109.8% | |
| MuSR (0-shot) | 7.6 | 6.3 | 83.2% | |
| Average | 27.6 | 26.5 | 96.1% | |
| Coding | HumanEval pass@1 | 67.3 | 67.1 | 99.7% |
| HumanEval+ pass@1 | 60.7 | 59.1 | 97.4% | |
| Multilingual | Portuguese MMLU (5-shot) | 59.96 | 58.69 | 97.9% |
| Spanish MMLU (5-shot) | 60.25 | 58.39 | 96.9% | |
| Italian MMLU (5-shot) | 59.23 | 57.82 | 97.6% | |
| German MMLU (5-shot) | 58.63 | 56.22 | 95.9% | |
| French MMLU (5-shot) | 59.65 | 57.58 | 96.5% | |
| Hindi MMLU (5-shot) | 50.10 | 47.14 | 94.1% | |
| Thai MMLU (5-shot) | 49.12 | 46.72 | 95.1% |
The results were obtained using the following commands:
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/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
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
--tasks mmlu_cot_0shot_llama_3.1_instruct \
--apply_chat_template \
--num_fewshot 0 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
--tasks arc_challenge_llama_3.1_instruct \
--apply_chat_template \
--num_fewshot 0 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
--tasks gsm8k_cot_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 8 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
--tasks hellaswag \
--num_fewshot 10 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
--tasks winogrande \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
--tasks truthfulqa \
--num_fewshot 0 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--apply_chat_template \
--fewshot_as_multiturn \
--tasks leaderboard \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_pt_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_es_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_it_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_de_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_fr_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_hi_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
--tasks mmlu_th_llama_3.1_instruct \
--fewshot_as_multiturn \
--apply_chat_template \
--num_fewshot 5 \
--batch_size auto
python3 codegen/generate.py \
--model neuralmagic/Meta-Llama-3.1-8B-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
Base model
meta-llama/Llama-3.1-8B