This model is a quantized version of Llama-3.1-Nemotron-70B-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. Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic achieves 99.41% recovery for the Arena-Hard evaluation, 100% for OpenLLM v1 (using Meta's prompting when available), and ToDo for OpenLLM v2.
This model was obtained by quantizing the weights and activations of Llama-3.1-Nemotron-70B-Instruct to FP8 data type, ready for inference with vLLM built from source. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.
Only the weights and activations of the linear operators within transformers blocks are quantized. Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the FP8 representations of the quantized weights and activations. Activations are also quantized on a per-token dynamic basis.
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 = "RedHatAI/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic"
number_gpus = 2
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)
vLLM aslo 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/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic
​​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-nemotron-70b-instruct-hf-fp8-dynamic:1.5
# Serve model via ilab
ilab model serve --model-path ~/.cache/instructlab/models/llama-3-1-nemotron-70b-instruct-hf-fp8-dynamic
# Chat with model
ilab model chat --model ~/.cache/instructlab/models/llama-3-1-nemotron-70b-instruct-hf-fp8-dynamic
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-Nemotron-70B-Instruct-HF-FP8-dynamic # OPTIONAL CHANGE
serving.kserve.io/deploymentMode: RawDeployment
name: Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic # 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-nemotron-70b-instruct-hf-fp8-dynamic: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-Nemotron-70B-Instruct-HF-FP8-dynamic",
"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 LLM-Compressor, as presented in the code snipet below.
import torch
from transformers import AutoTokenizer
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
from llmcompressor.transformers.compression.helpers import ( # noqa
calculate_offload_device_map,
custom_offload_device_map,
)
recipe = """
quant_stage:
quant_modifiers:
QuantizationModifier:
ignore: ["lm_head"]
config_groups:
group_0:
weights:
num_bits: 8
type: float
strategy: channel
dynamic: false
symmetric: true
input_activations:
num_bits: 8
type: float
strategy: token
dynamic: true
symmetric: true
targets: ["Linear"]
"""
model_stub = "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
model_name = model_stub.split("/")[-1]
device_map = calculate_offload_device_map(
model_stub, reserve_for_hessians=False, num_gpus=1, torch_dtype="auto"
)
model = SparseAutoModelForCausalLM.from_pretrained(
model_stub, torch_dtype="auto", device_map=device_map
)
output_dir = f"./{model_name}-FP8-dynamic"
oneshot(
model=model,
recipe=recipe,
output_dir=output_dir,
save_compressed=True,
tokenizer=AutoTokenizer.from_pretrained(model_stub),
)
This model was evaluated on the well-known Arena-Hard, OpenLLM v1, and OpenLLM v2. In all cases, model outputs were generated with the vLLM engine.
Arena-Hard evaluations were conducted using the Arena-Hard-Auto repository.
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.
| Benchmark | nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic (this model) |
Recovery |
| Arena Hard | 85.0 | 84.5 | 99.41% |
| OpenLLM Leaderboard v1 | 80.1 | 80.3 | 100.2% |
| OpenLLM Leaderboard v2 | 40.2 | 39.8 | 99.0% |
| Benchmark (per-task breakdown) | nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic (this model) | Recovery |
| OpenLLM v1 | |||
| MMLU (5-shot) | 83.51 | 83.49 | 99.97% |
| MMLU-cot (0-shot) | 85.89 | 86.18 | 100.33% |
| ARC Challenge (0-shot) | 93.09 | 93.09 | 100% |
| GSM-8K-cot (8-shot, strict-match) | 70.13 | 69.98 | 99.78% |
| Hellaswag (10-shot) | 87.39 | 87.22 | 99.80% |
| Winogrande (5-shot) | 84.93 | 84.93 | 100% |
| TruthfulQA (0-shot, mc2) | 55.97 | 57.12 | 102.05% |
| Average | 80.1 | 80.3 | 100.2% |
| OpenLLM v2 | |||
| MMLU-Pro (5-shot) | 43.45 | 42.99 | 98.94% |
| IFEval (0-shot) | 73.32 | 74.08 | 101.02% |
| BBH (3-shot) | 47.12 | 46.88 | 99.5% |
| Math-lvl-5 (4-shot) | 23.85 | 21.78 | 91.32% |
| MuSR (0-shot) | 13.5 | 13.35 | 98.88% |
| Average | 40.2 | 39.8 | 99% |
The results were obtained using the following commands:
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--tasks mmlu \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--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/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--tasks arc_challenge_llama_3.1_instruct \
--apply_chat_template \
--num_fewshot 0 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--tasks gsm8k_cot_llama_3.1_instruct \
--apply_chat_template \
--fewshot_as_multiturn \
--num_fewshot 8 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--tasks hellaswag \
--num_fewshot 10 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--tasks winogrande \
--num_fewshot 5 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
--tasks truthfulqa \
--num_fewshot 0 \
--batch_size auto
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True \
--apply_chat_template \
--fewshot_as_multiturn \
--tasks leaderboard \
--batch_size auto
Base model
meta-llama/Llama-3.1-70B