Qwen2.5-7B-Instruct-FP8-dynamic

Model Overview

• Model Architecture: Qwen2
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Activation quantization: FP8
  • Weight quantization: FP8
• Intended Use Cases: Intended for commercial and research use multiple languages. Similarly to Qwen2.5-7B, this models is intended for assistant-like chat.
• Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws).
• Release Date: 11/27/2024
• Version: 1.0
• License(s): apache-2.0
• Model Developers: Neural Magic

Model Optimizations

This model was obtained by quantizing activations and weights of Qwen2.5-7B-Instruct to FP8 data type. This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x). Weight quantization also reduces disk size requirements by approximately 50%.

Only weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme. The llm-compressor library is used for quantization.

Deployment

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/Qwen2.5-7B-Instruct-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "user", "content": "Give me a short introduction to large language model."},
]

prompts = tokenizer.apply_chat_template(messages, 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 aslo supports OpenAI-compatible serving. See the documentation for more details.

Creation

Creation details

This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.

from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot

# Load model
model_stub = "Qwen/Qwen2.5-7B-Instruct-FP8-dynamic"
model_name = model_stub.split("/")[-1]

tokenizer = AutoTokenizer.from_pretrained(model_stub)

model = AutoModelForCausalLM.from_pretrained(
    model_stub,
    device_map="auto",
    torch_dtype="auto",
)

# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_dynamic",
    ignore=["lm_head"],
)

# Apply quantization
oneshot(
    model=model,
    recipe=recipe,
)

# Save to disk in compressed-tensors format
save_path = model_name + "-FP8-dynamic"
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")

Evaluation

The model was evaluated on the OpenLLM leaderboard tasks (version 1) with the lm-evaluation-harness (commit 387Bbd54bc621086e05aa1b030d8d4d5635b25e6) and the vLLM engine, using the following command:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-7B-Instruct-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --tasks openllm \
  --batch_size auto

Accuracy

Open LLM Leaderboard evaluation scores

Benchmark	Qwen2.5-7B-Instruct	Qwen2.5-7B-Instruct-FP8-dynamic (this model)	Recovery
MMLU (5-shot)	74.24	74.04	99.7%
ARC Challenge (25-shot)	63.40	63.14	99.6%
GSM-8K (5-shot, strict-match)	80.36	80.06	99.6%
Hellaswag (10-shot)	81.52	81.11	99.5%
Winogrande (5-shot)	74.66	74.43	99.7%
TruthfulQA (0-shot, mc2)	64.76	64.87	100.2%
Average	73.16	72.94	99.7%