Files

SILONG ZENG 2e2aaa2fae [Doc][v0.18.0] Fix documentation formatting and improve code examples (#8701 )

### What this PR does / why we need it?
This PR fixes various documentation issues and improves code examples
throughout the project.

Signed-off-by: MrZ20 <2609716663@qq.com>

2026-04-28 09:01:25 +08:00

9.4 KiB

Raw Blame History

Using lm-eval

This document guides you to conduct accuracy testing using lm-eval.

Online Server

1. Start the vLLM server

You can run docker container to start the vLLM server on a single NPU:

   :substitutions:
# Update DEVICE according to your device (/dev/davinci[0-7])
export DEVICE=/dev/davinci7
# Update the vllm-ascend image
export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|
docker run --rm \
--name vllm-ascend \
--shm-size=1g \
--device $DEVICE \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-e VLLM_USE_MODELSCOPE=True \
-e PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 \
-it $IMAGE \
/bin/bash
vllm serve Qwen/Qwen2.5-0.5B-Instruct --max-model-len 4096 &

The vLLM server is started successfully, if you see logs as below:

INFO:     Started server process [9446]
INFO:     Waiting for application startup.
INFO:     Application startup complete.

2. Run GSM8K using the vLLM server (curl) and then run lm-eval for accuracy testing

You can query the result with input prompts:

PROMPT='<|im_start|>system
You are a professional accountant. Answer questions using accounting knowledge, output only the option letter (A/B/C/D).<|im_end|>
<|im_start|>user
Question: A company'"'"'s balance sheet as of December 31, 2023 shows:
  Current assets: Cash and equivalents 5 million yuan, Accounts receivable 8 million yuan, Inventory 6 million yuan
  Non-current assets: Net fixed assets 12 million yuan
  Current liabilities: Short-term loans 4 million yuan, Accounts payable 3 million yuan
  Non-current liabilities: Long-term loans 9 million yuan
  Owner'"'"'s equity: Paid-in capital 10 million yuan, Retained earnings ?
Requirement: Calculate the company'"'"'s Asset-Liability Ratio and Current Ratio (round to two decimal places).
Options:
A. Asset-Liability Ratio=58.33%, Current Ratio=1.90
B. Asset-Liability Ratio=62.50%, Current Ratio=2.17
C. Asset-Liability Ratio=65.22%, Current Ratio=1.75
D. Asset-Liability Ratio=68.00%, Current Ratio=2.50<|im_end|>
<|im_start|>assistant
'

curl http://localhost:8000/v1/completions \
    -H "Content-Type: application/json" \
    -d "$(jq -n \
        --arg model "Qwen/Qwen2.5-0.5B-Instruct" \
        --arg prompt "$PROMPT" \
        '{
            model: $model,
            prompt: $prompt,
            max_completion_tokens: 1,
            temperature: 0,
            stop: ["<|im_end|>"]
        }')" | python3 -m json.tool

The output format matches the following:

{
    "id": "cmpl-2f678e8bdf5a4b209a3f2c1fa5832e25",
    "object": "text_completion",
    "created": 1754475138,
    "model": "Qwen/Qwen2.5-0.5B-Instruct",
    "choices": [
        {
            "index": 0,
            "text": "A",
            "logprobs": null,
            "finish_reason": "length",
            "stop_reason": null,
            "prompt_logprobs": null
        }
    ],
    "service_tier": null,
    "system_fingerprint": null,
    "usage": {
        "prompt_tokens": 252,
        "total_tokens": 253,
        "completion_tokens": 1,
        "prompt_tokens_details": null
    },
    "kv_transfer_params": null
}

Install lm-eval in the container:

export HF_ENDPOINT="https://hf-mirror.com"
export USE_MODELSCOPE_HUB=0
pip install lm-eval[api]

:::{note} The Docker container is launched with VLLM_USE_MODELSCOPE=True, which may cause lm-eval to download datasets from ModelScope instead of HuggingFace. Setting USE_MODELSCOPE_HUB=0 disables this behavior so that lm-eval can fetch datasets from HuggingFace correctly. :::

Run the following command:

# Only test gsm8k dataset in this demo
lm_eval \
  --model local-completions \
  --model_args model=Qwen/Qwen2.5-0.5B-Instruct,base_url=http://127.0.0.1:8000/v1/completions,tokenized_requests=False,trust_remote_code=True \
  --tasks gsm8k \
  --output_path ./

After 30 minutes, the output is as shown below:

The markdown format results is as below:

|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.3215|±  |0.0129|
|gsm8k|      3|strict-match    |     5|exact_match|↑  |0.2077|±  |0.0112|

Offline Server

1. Run docker container

You can run docker container on a single NPU:

   :substitutions:
# Update DEVICE according to your device (/dev/davinci[0-7])
export DEVICE=/dev/davinci7
# Update the vllm-ascend image
export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|
docker run --rm \
--name vllm-ascend \
--shm-size=1g \
--device $DEVICE \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-e VLLM_USE_MODELSCOPE=True \
-e PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 \
-it $IMAGE \
/bin/bash

2. Run GSM8K using lm-eval for accuracy testing

Install lm-eval in the container:

export HF_ENDPOINT="https://hf-mirror.com"
export USE_MODELSCOPE_HUB=0
pip install lm-eval

Run the following command:

# Only test gsm8k dataset in this demo
lm_eval \
  --model vllm \
  --model_args pretrained=Qwen/Qwen2.5-0.5B-Instruct,max_model_len=4096 \
  --tasks gsm8k \
  --batch_size auto

After 1 to 2 minutes, the output is shown below:

The markdown format results is as below:

Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.3412|±  |0.0131|
|gsm8k|      3|strict-match    |     5|exact_match|↑  |0.3139|±  |0.0128|

Use Offline Datasets

Take GSM8K (single dataset) and MMLU (multi-subject dataset) as examples, and you can see more from using-local-datasets.

# set HF_DATASETS_OFFLINE when using offline datasets
export HF_DATASETS_OFFLINE=1
git clone https://github.com/EleutherAI/lm-evaluation-harness.git
cd lm-evaluation-harness
pip install -e .
# gsm8k yaml path
cd lm_eval/tasks/gsm8k
# mmlu yaml path
cd lm_eval/tasks/mmlu/default

Set gsm8k.yaml as follows:

tag:
  - math_word_problems
task: gsm8k

# set dataset_path arrow or json or parquet according to the downloaded dataset
dataset_path: arrow

# set dataset_name to null
dataset_name: null
output_type: generate_until

# add dataset_kwargs 
dataset_kwargs:
  data_files:
    # train and test data download path
    train: /root/.cache/gsm8k/gsm8k-train.arrow
    test: /root/.cache/gsm8k/gsm8k-test.arrow

training_split: train
fewshot_split: train
test_split: test
doc_to_text: 'Q: {{question}}
  A(Please follow the summarized result at the end with the format of "The answer is xxx", where xx is the result.):'
doc_to_target: "{{answer}}" #" {{answer.split('### ')[-1].rstrip()}}"
metric_list:
  - metric: exact_match
    aggregation: mean
    higher_is_better: true
    ignore_case: true
    ignore_punctuation: false
    regexes_to_ignore:
      - ","
      - "\\$"
      - "(?s).*#### "
      - "\\.$"
generation_kwargs:
  until:
    - "Question:"
    - "</s>"
    - "<|im_end|>"
  do_sample: false
  temperature: 0.0
repeats: 1
num_fewshot: 5
filter_list:
  - name: "strict-match"
    filter:
      - function: "regex"
        regex_pattern: "#### (\\-?[0-9\\.\\,]+)"
      - function: "take_first"
  - name: "flexible-extract"
    filter:
      - function: "regex"
        group_select: -1
        regex_pattern: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
      - function: "take_first"
metadata:
  version: 3.0

Set _default_template_yaml as follows:

# set dataset_path according to the downloaded dataset
dataset_path: /root/.cache/mmlu
test_split: test
fewshot_split: dev
fewshot_config:
  sampler: first_n
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
metadata:
  version: 1.0
dataset_kwargs:
  trust_remote_code: true

You can see more usage on Lm-eval Docs.

9.4 KiB Raw Blame History