Quantized Model Information

[!IMPORTANT] This repository is an AWQ 4-bit quantized version of meta-llama/Llama-3.3-70B-Instruct, originally released by Meta AI.

This model was quantized using AutoAWQ from FP16 down to INT4 using GEMM kernels, with zero-point quantization and a group size of 128.

Hardware: Intel Xeon CPU E5-2699A v4 @ 2.40GHz, 256GB of RAM, and 2x NVIDIA RTX 3090.

Model usage (inference) information for Transformers, AutoAWQ, Text Generation Interface (TGI), and vLLM , as well as quantization reproduction details, are below.

Original Model Information

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Model Usage

In order to use this quantized model, support is offered for different solutions such as transformers, autoawq, or text-generation-inference.

[!NOTE] In order to run inference with Llama 3.3 70B Instruct AWQ in INT4, around 35 GiB of VRAM are needed for loading the model checkpoint, without including the KV cache or the CUDA graphs, meaning that there should be a bit over that VRAM available.

🤗 Transformers

In order to run inference with Llama 3.3 70B Instruct AWQ in INT4, you need to install the following packages:

Bash

pip install -q --upgrade transformers autoawq accelerate

To run inference of Llama 3.3 70B Instruct AWQ in INT4 precision, the AWQ model can be instantiated as any other causal language modeling model via AutoModelForCausalLM. Run inference as usual.

Python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AwqConfig

model_id = "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4"
quantization_config = AwqConfig(
    bits=4,
    fuse_max_seq_len=512, # Note: Update this as per your use-case
    do_fuse=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.float16,
  low_cpu_mem_usage=True,
  device_map="auto",
  quantization_config=quantization_config
)

prompt = [
  {"role": "system", "content": "You are a helpful assistant, that responds as a pirate."},
  {"role": "user", "content": "What's Deep Learning?"},
]
inputs = tokenizer.apply_chat_template(
  prompt,
  tokenize=True,
  add_generation_prompt=True,
  return_tensors="pt",
  return_dict=True,
).to("cuda")

outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256)
print(tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0])

AutoAWQ

In order to run inference with Llama 3.3 70B Instruct AWQ in INT4, you need to install the following packages:

Bash

pip install -q --upgrade transformers autoawq accelerate

Alternatively, one may want to run that via AutoAWQ even though it's built on top of 🤗 transformers, which is the recommended approach instead as described above.

Python

import torch
from awq import AutoAWQForCausalLM
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoAWQForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.float16,
  low_cpu_mem_usage=True,
  device_map="auto",
)

prompt = [
  {"role": "system", "content": "You are a helpful assistant, that responds as a pirate."},
  {"role": "user", "content": "What's Deep Learning?"},
]
inputs = tokenizer.apply_chat_template(
  prompt,
  tokenize=True,
  add_generation_prompt=True,
  return_tensors="pt",
  return_dict=True,
).to("cuda")

outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256)
print(tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0])

The AutoAWQ script has been adapted from AutoAWQ/examples/generate.py.

🤗 Text Generation Inference (TGI)

To run the text-generation-launcher with Llama 3.3 70B Instruct AWQ in INT4 with Marlin kernels for optimized inference speed, you will need to have Docker installed (see installation notes) and the huggingface_hub Python package as you need to login to the Hugging Face Hub.

Bash

pip install -q --upgrade huggingface_hub
huggingface-cli login

Then you just need to run the TGI v2.2.0 (or higher) Docker container as follows:

Bash

docker run --gpus all --shm-size 1g -ti -p 8080:80 \
  -v hf_cache:/data \
  -e MODEL_ID=ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4 \
  -e NUM_SHARD=4 \
  -e QUANTIZE=awq \
  -e HF_TOKEN=$(cat ~/.cache/huggingface/token) \
  -e MAX_INPUT_LENGTH=4000 \
  -e MAX_TOTAL_TOKENS=4096 \
  ghcr.io/huggingface/text-generation-inference:2.2.0

[!NOTE] TGI will expose different endpoints, to see all the endpoints available check TGI OpenAPI Specification.

To send request to the deployed TGI endpoint compatible with OpenAI OpenAPI specification i.e. /v1/chat/completions:

Bash

curl 0.0.0.0:8080/v1/chat/completions \
  -X POST \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "tgi",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is Deep Learning?"
      }
    ],
    "max_tokens": 128
  }'

Or programatically via the huggingface_hub Python client as follows:

Python

import os
from huggingface_hub import InferenceClient

client = InferenceClient(base_url="http://0.0.0.0:8080", api_key=os.getenv("HF_TOKEN", "-"))

chat_completion = client.chat.completions.create(
  model="ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is Deep Learning?"},
  ],
  max_tokens=128,
)

Alternatively, the OpenAI Python client can also be used (see installation notes) as follows:

Python

import os
from openai import OpenAI

client = OpenAI(base_url="http://0.0.0.0:8080/v1", api_key=os.getenv("OPENAI_API_KEY", "-"))

chat_completion = client.chat.completions.create(
  model="tgi",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is Deep Learning?"},
  ],
  max_tokens=128,
)

vLLM

To run vLLM with Llama 3.3 70B Instruct AWQ in INT4, you will need to have Docker installed (see installation notes) and run the latest vLLM Docker container as follows:

Bash

docker run --runtime nvidia --gpus all --ipc=host -p 8000:8000 \
  -v hf_cache:/root/.cache/huggingface \
  vllm/vllm-openai:latest \
  --model ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4 \
  --tensor-parallel-size 4 \
  --max-model-len 4096

To send request to the deployed vLLM endpoint compatible with OpenAI OpenAPI specification i.e. /v1/chat/completions:

Bash

curl 0.0.0.0:8000/v1/chat/completions \
  -X POST \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is Deep Learning?"
      }
    ],
    "max_tokens": 128
  }'

Or programatically via the openai Python client (see installation notes) as follows:

Python

import os
from openai import OpenAI

client = OpenAI(base_url="http://0.0.0.0:8000/v1", api_key=os.getenv("VLLM_API_KEY", "-"))

chat_completion = client.chat.completions.create(
  model="ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is Deep Learning?"},
  ],
  max_tokens=128,
)

Quantization Reproduction Information

[!NOTE] In order to quantize Llama 3.3 70B Instruct using AutoAWQ, you will need to use an instance with at least enough CPU RAM to fit the whole model i.e. ~140GiB, and an NVIDIA GPU with 40GiB of VRAM to quantize it.

In order to quantize Llama 3.3 70B Instruct, first install the following packages:

Bash

pip install -q --upgrade transformers autoawq accelerate

This quantization was produced using a single node with an Intel Xeon CPU E5-2699A v4 @ 2.40GHz, 256GB of RAM, and 2x NVIDIA RTX 3090 (24GB VRAM each, for a total of 48 GB VRAM).

I initially adapted hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4, so many thanks to the Hugging Quants team, the AutoAWQ team, and the MIT HAN Lab for LLM-AWQ. I'd also like to thank Professor David Dobolyi over at University of Colorado Boulder and Marc Sun at Hugging Face for their work, specifically AutoAWQ PR#630.

Adapted from AutoAWQ/examples/quantize.py and hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4:

Python

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
import torch

# Empty Cache
torch.cuda.empty_cache()

# Memory Limits - Set this according to your hardware limits
max_memory = {0: "22GiB", 1: "22GiB", "cpu": "160GiB"}

model_path = "meta-llama/Llama-3.3-70B-Instruct"
quant_path = "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4"
quant_config = {
  "zero_point": True,
  "q_group_size": 128,
  "w_bit": 4,
  "version": "GEMM"
  
}

# Load model - Note: while this loads the layers into the CPU, the GPUs (and the VRAM) are still required for quantization! (Verified with nvida-smi)
model = AutoAWQForCausalLM.from_pretrained(
    model_path,
    use_cache=False,
    max_memory=max_memory,
    device_map="cpu"
)

tokenizer = AutoTokenizer.from_pretrained(model_path)

# Quantize
model.quantize(
    tokenizer,
    quant_config=quant_config
)

# Save quantized model
model.save_quantized(quant_path)
tokenizer.save_pretrained(quant_path)

print(f'Model is quantized and saved at "{quant_path}"')

import torch from transformers import AutoModelForCausalLM, AutoTokenizer, AwqConfig model_id = "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4" quantization_config = AwqConfig( bits=4, fuse_max_seq_len=512, # Note: Update this as per your use-case do_fuse=True, ) tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto", quantization_config=quantization_config ) prompt = [ {"role": "system", "content": "You are a helpful assistant, that responds as a pirate."}, {"role": "user", "content": "What's Deep Learning?"}, ] inputs = tokenizer.apply_chat_template( prompt, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True, ).to("cuda") outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256) print(tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0])

import torch from awq import AutoAWQForCausalLM from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoAWQForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto", ) prompt = [ {"role": "system", "content": "You are a helpful assistant, that responds as a pirate."}, {"role": "user", "content": "What's Deep Learning?"}, ] inputs = tokenizer.apply_chat_template( prompt, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True, ).to("cuda") outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256) print(tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0])

docker run --gpus all --shm-size 1g -ti -p 8080:80 \ -v hf_cache:/data \ -e MODEL_ID=ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4 \ -e NUM_SHARD=4 \ -e QUANTIZE=awq \ -e HF_TOKEN=$(cat ~/.cache/huggingface/token) \ -e MAX_INPUT_LENGTH=4000 \ -e MAX_TOTAL_TOKENS=4096 \ ghcr.io/huggingface/text-generation-inference:2.2.0

curl 0.0.0.0:8080/v1/chat/completions \ -X POST \ -H 'Content-Type: application/json' \ -d '{ "model": "tgi", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What is Deep Learning?" } ], "max_tokens": 128 }'

import os from huggingface_hub import InferenceClient client = InferenceClient(base_url="http://0.0.0.0:8080", api_key=os.getenv("HF_TOKEN", "-")) chat_completion = client.chat.completions.create( model="ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is Deep Learning?"}, ], max_tokens=128, )

import os from openai import OpenAI client = OpenAI(base_url="http://0.0.0.0:8080/v1", api_key=os.getenv("OPENAI_API_KEY", "-")) chat_completion = client.chat.completions.create( model="tgi", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is Deep Learning?"}, ], max_tokens=128, )

docker run --runtime nvidia --gpus all --ipc=host -p 8000:8000 \ -v hf_cache:/root/.cache/huggingface \ vllm/vllm-openai:latest \ --model ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4 \ --tensor-parallel-size 4 \ --max-model-len 4096

curl 0.0.0.0:8000/v1/chat/completions \ -X POST \ -H 'Content-Type: application/json' \ -d '{ "model": "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What is Deep Learning?" } ], "max_tokens": 128 }'

import os from openai import OpenAI client = OpenAI(base_url="http://0.0.0.0:8000/v1", api_key=os.getenv("VLLM_API_KEY", "-")) chat_completion = client.chat.completions.create( model="ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is Deep Learning?"}, ], max_tokens=128, )

from awq import AutoAWQForCausalLM from transformers import AutoTokenizer import torch # Empty Cache torch.cuda.empty_cache() # Memory Limits - Set this according to your hardware limits max_memory = {0: "22GiB", 1: "22GiB", "cpu": "160GiB"} model_path = "meta-llama/Llama-3.3-70B-Instruct" quant_path = "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4" quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" } # Load model - Note: while this loads the layers into the CPU, the GPUs (and the VRAM) are still required for quantization! (Verified with nvida-smi) model = AutoAWQForCausalLM.from_pretrained( model_path, use_cache=False, max_memory=max_memory, device_map="cpu" ) tokenizer = AutoTokenizer.from_pretrained(model_path) # Quantize model.quantize( tokenizer, quant_config=quant_config ) # Save quantized model model.save_quantized(quant_path) tokenizer.save_pretrained(quant_path) print(f'Model is quantized and saved at "{quant_path}"')

Meta Llama 3.3 70B Instruct AWQ INT4

Quantized Model Information

Original Model Information

Model Usage

🤗 Transformers

AutoAWQ

🤗 Text Generation Inference (TGI)

vLLM

Quantization Reproduction Information

Meta Llama 3.3 70B Instruct AWQ INT4

Quantized Model Information

Original Model Information

Model Usage

🤗 Transformers

AutoAWQ

🤗 Text Generation Inference (TGI)

vLLM

Quantization Reproduction Information