mistral-indo-7b / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
fe1b9df verified
|
raw
history blame
5.22 kB
metadata
language:
  - id
license: apache-2.0
tags:
  - mistral
  - text-generation-inference
model-index:
  - name: mistral-indo-7b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 61.09
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sarahlintang/mistral-indo-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 81.19
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sarahlintang/mistral-indo-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 62.99
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sarahlintang/mistral-indo-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 42.34
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sarahlintang/mistral-indo-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 78.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sarahlintang/mistral-indo-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 32.07
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sarahlintang/mistral-indo-7b
          name: Open LLM Leaderboard

mistral-indo-7b

Mistral 7b v0.1 fine-tuned on Indonesian's instructions dataset.

Prompt template:

### Human: {Instruction}### Assistant: {response}

Example of Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer, GenerationConfig

model_id = "sarahlintang/mistral-indo-7b"

model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).to("cuda")
tokenizer = AutoTokenizer.from_pretrained(model_id)

def create_instruction(instruction):
    prompt = f"### Human: {instruction} ### Assistant: "
    return prompt


def generate(
        instruction,
        max_new_tokens=128,
        temperature=0.1,
        top_p=0.75,
        top_k=40,
        num_beams=4,
        **kwargs
):
    
    prompt = create_instruction(instruction)
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].to("cuda")
    attention_mask = inputs["attention_mask"].to("cuda")
    generation_config = GenerationConfig(
        temperature=temperature,
        top_p=top_p,
        top_k=top_k,
        num_beams=num_beams,
        **kwargs,
    )
    with torch.no_grad():
        generation_output = model.generate(
            input_ids=input_ids,
            attention_mask=attention_mask,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=max_new_tokens,
            early_stopping=True
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Assistant:")[1].strip()

instruction = "Sebutkan lima macam makanan khas Indonesia."
print(generate(instruction))

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 59.68
AI2 Reasoning Challenge (25-Shot) 61.09
HellaSwag (10-Shot) 81.19
MMLU (5-Shot) 62.99
TruthfulQA (0-shot) 42.34
Winogrande (5-shot) 78.37
GSM8k (5-shot) 32.07