serhii.net

lm_eval --model hf \
    --model_args pretrained=EleutherAI/pythia-160m,revision=step100000,dtype="float" \
    --tasks lambada_openai,hellaswag \
    --device cuda:0 \
    --batch_size 8

task: coqa
dataset_path: EleutherAI/coqa
output_type: generate_until
training_split: train
validation_split: validation
doc_to_text: !function utils.doc_to_text
doc_to_target: !function utils.doc_to_target
process_results: !function utils.process_results
should_decontaminate: true
doc_to_decontamination_query: "{{story}} {{question.input_text|join('\n')}}"
generation_kwargs:
  until:
    - "\nQ:"
metric_list:
  - metric: em
    aggregation: mean
    higher_is_better: true
  - metric: f1
    aggregation: mean
    higher_is_better: true

export HF_HOME="~/.cache/huggingface"
export AZURE_OPENAI_API_KEY=""
export AZURE_OPENAI_API_BASE=""
export AZURE_OPENAI_API_VERSION="2023-07-01-preview"

# pip install git+https://github.com/EvolvingLMMs-Lab/lmms-eval.git
python3 -m lmms_eval \
    --model openai_compatible \
    --model_args model_version=gpt-4o-2024-11-20,azure_openai=True \
    --tasks mme,mmmu_val \
    --batch_size 1

oaieval gpt-3.5-turbo test-match

{
  "input": [
    {
      "role": "system",
      "content": "You are an assistant with knowledge of U.S. state laws. Answer the questions accurately."
    },
    {
      "role": "user",
      "content": "List the states where adultery is technically illegal. Only provide a list of states with no explanation."
    }
  ],
  "ideal": "Alabama, Arizona, Florida, Idaho, Illinois, Kansas, Michigan, Minnesota, Mississippi, New York, North Carolina, Oklahoma, Rhode Island, South Carolina, Virginia, Wisconsin, Georgia"
}

<eval_name>:
  id: <eval_name>.dev.v0
  description: <description>
  metrics: [accuracy]

<eval_name>.dev.v0:
  class: evals.elsuite.basic.match:Match
  args:
    samples_jsonl: <eval_name>/samples.jsonl

humor_likert:
  prompt: |-
    Is the following funny?

    {completion}

    Answer using the scale of 1 to 5, where 5 is the funniest.
  choice_strings: "12345"
  choice_scores: from_strings
  input_outputs:
    input: completion

closedqa:            config_dict = yaml.load(yaml_path.read_text())
  prompt: |-
    You are assessing a submitted answer on a given task based on a criterion. Here is the data:
    [BEGIN DATA]
    ***
    [Task]: {input}
    ***
    [Submission]: {completion}
    ***
    [Criterion]: {criteria}
    ***
    [END DATA]
    Does the submission meet the criterion? First, write out in a step by step manner your reasoning about the criterion to be sure that your conclusion is correct. Avoid simply stating the correct answers at the outset. Then print only the single character "Y" or "N" (without quotes or punctuation) on its own line corresponding to the correct answer. At the end, repeat just the letter again by itself on a new line.

    Reasoning:
  eval_type: cot_classify
  choice_scores:
    "Y": 1.0
    "N": 0.0
  choice_strings: 'YN'
  input_outputs:
    input: "completion"

langchain/llm/text-davinci-003:
  class: evals.completion_fns.langchain_llm:LangChainLLMCompletionFn
  args:
    llm: OpenAI
    llm_kwargs:
      model_name: text-davinci-003

langchain/llm/flan-t5-xl:
  class: evals.completion_fns.langchain_llm:LangChainLLMCompletionFn
  args:
    llm: HuggingFaceHub
    llm_kwargs:
      repo_id: google/flan-t5-xl

lighteval accelerate \
     "model_name=openai-community/gpt2" \
     "leaderboard|truthfulqa:mc|0|0"

    return Doc(
        instruction=ZEROSHOT_QA_INSTRUCTION,
        task_name=task_name,
        query=ZEROSHOT_QA_USER_PROMPT.format(question=line["question"], options=options),
        choices=line["choices"],
        gold_index=gold_index,
    )

yourbench_mcq = LightevalTaskConfig(
    name="HF_TASK_NAME",  # noqa: F821
    suite=["custom"],
    prompt_function=yourbench_prompt,
    hf_repo="HF_DATASET_NAME",  # noqa: F821
    hf_subset="lighteval",
    hf_avail_splits=["train"],
    evaluation_splits=["train"],
    few_shots_split=None,
    few_shots_select=None,
    generation_size=8192,
    metric=[Metrics.yourbench_metrics],
    trust_dataset=True,
    version=0,
)

model_parameters:
  model_name: "openai/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
  provider: "openai"
  base_url: "https://router.huggingface.co/hf-inference/v1"
  generation_parameters:
    temperature: 0.5
    max_new_tokens: 256
    top_p: 0.9
    seed: 0
    repetition_penalty: 1.0
    frequency_penalty: 0.0

# Run benchmark 
helm-run --run-entries mmlu:subject=philosophy,model=openai/gpt2 --suite my-suite --max-eval-instances 10 
# Summarize benchmark results 
helm-summarize --suite my-suite

  - name: huggingface/gemma-2-9b-it
    model_name: google/gemma-2-9b-it
    tokenizer_name: google/gemma-2-9b
    max_sequence_length: 8192
    client_spec:
      class_name: "helm.clients.huggingface_client.HuggingFaceClient"
      args:
        device_map: auto
        torch_dtype: torch.bfloat16

# model_cfg.py
from opencompass.models import HuggingFaceCausalLM

models = [
    dict(
        type=HuggingFaceCausalLM,
        path='huggyllama/llama-7b',
        model_kwargs=dict(device_map='auto'),
        tokenizer_path='huggyllama/llama-7b',
        tokenizer_kwargs=dict(padding_side='left', truncation_side='left'),
        max_seq_len=2048,
        max_out_len=50,
        run_cfg=dict(num_gpus=8, num_procs=1),
    )
]

from opencompass.models import OpenAI

models = [
    dict(
        type=OpenAI,                             # Using the OpenAI model
        # Parameters for `OpenAI` initialization
        path='gpt-4',                            # Specify the model type
        key='YOUR_OPENAI_KEY',                   # OpenAI API Key
        max_seq_len=2048,                        # The max input number of tokens
        # Common parameters shared by various models, not specific to `OpenAI` initialization.
        abbr='GPT-4',                            # Model abbreviation used for result display.
        max_out_len=512,                         # Maximum number of generated tokens.
        batch_size=1,                            # The size of a batch during inference.
        run_cfg=dict(num_gpus=0),                # Resource requirements (no GPU needed)
    ),
]

import pytest
from deepeval import assert_test
from deepeval.metrics import GEval
from deepeval.test_case import LLMTestCase, LLMTestCaseParams

def test_case():
    correctness_metric = GEval(
        name="Correctness",
        criteria="Determine if the 'actual output' is correct based on the 'expected output'.",
        evaluation_params=[LLMTestCaseParams.ACTUAL_OUTPUT, LLMTestCaseParams.EXPECTED_OUTPUT],
        threshold=0.5
    )
    test_case = LLMTestCase(
        input="What if these shoes don't fit?",
        # Replace this with the actual output from your LLM application
        actual_output="You have 30 days to get a full refund at no extra cost.",
        expected_output="We offer a 30-day full refund at no extra costs.",
        retrieval_context=["All customers are eligible for a 30 day full refund at no extra costs."]
    )
    assert_test(test_case, [correctness_metric])

deepeval set-local-model --model-name=<model_name> \  
--base-url="http://localhost:8000/v1/" \  
--api-key=<api-key>

model_list:
  # - model_name: github-Llama-3.2-11B-Vision-Instruct # Model Alias to use for requests
  - model_name: minist # Model Alias to use for requests
    litellm_params:
      model: github/Ministral-3B
      api_key: "os.environ/GITHUB_API_KEY" # ensure you have `GITHUB_API_KEY` in your .env

{
    "minist": {
        "model_name": "minist",
        "api_base": "http://0.0.0.0:4000/v1",
        "api_type": "openai",
        "api_key": "whatever",
        "anony_only": false
    }
}

echo -e '\e[1mbold\e[22m'
echo -e '\e[2mdim\e[22m'
echo -e '\e[3mitalic\e[23m'
echo -e '\e[4munderline\e[24m'
echo -e '\e[4:1mthis is also underline (since 0.52)\e[4:0m'
echo -e '\e[21mdouble underline (since 0.52)\e[24m'
echo -e '\e[4:2mthis is also double underline (since 0.52)\e[4:0m'
echo -e '\e[4:3mcurly underline (since 0.52)\e[4:0m'
echo -e '\e[4:4mdotted underline (since 0.76)\e[4:0m'
echo -e '\e[4:5mdashed underline (since 0.76)\e[4:0m'
echo -e '\e[5mblink (since 0.52)\e[25m'
echo -e '\e[7mreverse\e[27m'
echo -e '\e[8minvisible\e[28m <- invisible (but copy-pasteable)'
echo -e '\e[9mstrikethrough\e[29m'
echo -e '\e[53moverline (since 0.52)\e[55m'

echo -e '\e[31mred\e[39m'
echo -e '\e[91mbright red\e[39m'
echo -e '\e[38:5:42m256-color, de jure standard (ITU-T T.416)\e[39m'
echo -e '\e[38;5;42m256-color, de facto standard (commonly used)\e[39m'
echo -e '\e[38:2::240:143:104mtruecolor, de jure standard (ITU-T T.416) (since 0.52)\e[39m'
echo -e '\e[38:2:240:143:104mtruecolor, rarely used incorrect format (might be removed at some point)\e[39m'
echo -e '\e[38;2;240;143;104mtruecolor, de facto standard (commonly used)\e[39m'

echo -e '\e[46mcyan background\e[49m'
echo -e '\e[106mbright cyan background\e[49m'
echo -e '\e[48:5:42m256-color background, de jure standard (ITU-T T.416)\e[49m'
echo -e '\e[48;5;42m256-color background, de facto standard (commonly used)\e[49m'
echo -e '\e[48:2::240:143:104mtruecolor background, de jure standard (ITU-T T.416) (since 0.52)\e[49m'
echo -e '\e[48:2:240:143:104mtruecolor background, rarely used incorrect format (might be removed at some point)\e[49m'
echo -e '\e[48;2;240;143;104mtruecolor background, de facto standard (commonly used)\e[49m'

echo -e '\e[21m\e[58:5:42m256-color underline (since 0.52)\e[59m\e[24m'
echo -e '\e[21m\e[58;5;42m256-color underline (since 0.52)\e[59m\e[24m'
echo -e '\e[4:3m\e[58:2::240:143:104mtruecolor underline (since 0.52) (*)\e[59m\e[4:0m'
echo -e '\e[4:3m\e[58:2:240:143:104mtruecolor underline (since 0.52) (might be removed at some point) (*)\e[59m\e[4:0m'
echo -e '\e[4:3m\e[58;2;240;143;104mtruecolor underline (since 0.52) (*)\e[59m\e[4:0m'

time alacritty -e bash -c exit
time gnome-terminal -e "bash -c exit"
time kitty --single-instance bash -c exit

[keyboard]
bindings = [
   { key = "Return", mods = "Control|Shift", action = "SpawnNewInstance" }
]

[hints]
alphabet = "aoeusndh"

hints.enabled
action = "Copy"
# command = "xdg-open" # On Linux/BSD
hyperlinks = true
post_processing = true
persist = false
mouse.enabled = true
binding = { key = "N", mods = "Control|Shift" }

# adds file paths as well
regex = '(?:(?:ipfs:|ipns:|magnet:|mailto:|gemini://|gopher://|https?://|news:|git://|ssh:|ftp:|file:)[^\u0000-\u001F\u007F-\u009F<>"\s{}\-\^⟨⟩`\\]+|(?:(?:\.\.?/)+|/)[^\u0000-\u001F\u007F-\u009F<>"\s{}\-\^⟨⟩`\\]+)'
# regex = "(ipfs:|ipns:|magnet:|mailto:|gemini://|gopher://|https://|http://|news:|file:|git://|ssh:|ftp://)[^\u0000-\u001F\u007F-\u009F<>\"\\s{-}\\^⟨⟩`\\\\]+"

## Bindings

# https://sw.kovidgoyal.net/kitty/index.html#kittens
map kitty_mod>f1 launch --stdin-source=@screen_scrollback --stdin-add-formatting less +G -R

## Hints
# File paths
map kitty_mod+n>f kitten hints --type path --program @

# IPs (+ with ports)
map kitty_mod+n>i kitten hints --type regex --regex [0-9]+(?:\.[0-9]+){3} --program @
map kitty_mod+n>p kitten hints --type regex --regex [0-9]+(?:\.[0-9]+){3}:[0-9]+ --program @

# CLI Commands
# map kitty_mod+n>c kitten hints --type regex --regex "(\$|>)(.+)(?:\n|\s*$)?" --program @
# This version copies up to the vim mode indicator
# map kitty_mod+n>c kitten hints --type regex --regex "(\$|>)(.+?)(?:\n|\s+$|\s+(?:INS|VIS|REP|SEA))" --program @
# map kitty_mod+n>c kitten hints --type regex --regex "\$(.+)" --program @

# Linenum
map kitty_mod+n>l kitten hints --type line --program @

# https://sw.kovidgoyal.net/kitty/index.html#kittens
map kitty_mod>f1 launch --stdin-source=@screen_scrollback --stdin-add-formatting less +G -R
scrollback_pager vim - -c "w! /tmp/kitty_scrollback_sh" -c "term ++curwin cat /tmp/kitty_scrollback_sh"