Qwen/Qwen2.5-7B-Instruct

Overview

Qwen2.5-7B-Instruct is a large language model with 7B parameters, capable of performing text-to-text generation with a wide range of tasks. The model is trained on a large amount of data, and is capable of handling long-form inputs.

Prerequisites

• vLLM version: 0.17.0
• Config: GPUs = 1x VA16, Precision = INT4, TP = 4, max-model-len = 64K

Example config only. Refer to above for others.

Start Docker Container

docker run \
  --privileged=true \
  --name vllm_service \
  --shm-size=256g \
  --ipc=host \
  -p 8000:8000 \
  -it \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  harbor.vastaitech.com/ai_deliver/vllm_vacc:latest \
  bash

Launching the Server

INT4 on 1x VA16

export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
vllm serve Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4 \
  --trust-remote-code \
  --tensor-parallel-size 4 \
  --max-model-len 65536 \
  --enable-auto-tool-choice --tool-call-parser hermes \
    --hf-overrides '{"rope_parameters":{"factor":2,"original_max_position_embeddings":32768,"rope_theta":1000000,"rope_type":"yarn"}}'
  --enforce-eager

Client Usage

from openai import OpenAI

client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")
resp = client.chat.completions.create(
    model="Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4",
    messages=[{"role": "user", "content": "Explain gated delta networks in one paragraph."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

References

• Qwen2.5-7B-Instruct on Hugging Face
• GPTQ INT4 checkpoint