Update src/display/about.py

src/display/about.py

@@ -20,27 +20,21 @@ Kaz LLM is a benchmark for LLM with multiple-choice tasks on the following topic
 - mmlu-translated-kk
 - kazakh-constitution-mc
 - kazakh-dastur-mc
-- kazakh-unified-national-testing-mc
+- kazakh-unified-national-testing-mc(biology,english, geography, history of kz, world's history, society rights, literature, kazakh language)
 
 Each task contains from 4 to 8 answer choices.
 ## Instructions for Use
 ### Installation
 To install the necessary library, run the following command:
 ```bash
-git clone --depth 1 https://github.com/horde-research/lm-evaluation-harness-kk.git
-cd lm-evaluation-harness-kk
-pip install -e .
+git clone https://github.com/horde-research/horde-common.git
+cd scripts
+pip install -r requirements.txt
 ```
 ### Execution
 To run the benchmark, use the following command:
 ```bash
-lm_eval \
-    --model hf \
-    --model_args pretrained={hf/model} \
-    --batch_size 8 \
-    --num_fewshot 0 \
-    --tasks mmlu_translated_kk,kazakh_and_literature_unt_mc,kk_biology_unt_mc,kk_constitution_mc,kk_dastur_mc,kk_english_unt_mc,kk_geography_unt_mc,kk_history_of_kazakhstan_unt_mc,kk_human_society_rights_unt_mc,kk_unified_national_testing_mc,kk_world_history_unt_mc \
-    --output output
+python mc-eval-simplified-inference.py --model_id deepseek-ai/DeepSeek-R1-Distill-Qwen-14B --output_path .
 ```
 ### Results
 After executing the above command, a JSON file will be created in the `output` directory, which must be attached. This file contains the results of the tasks and a description of the session, and **must not be modified**.
@@ -55,7 +49,7 @@ Kaz LLM – бұл төмендегі тақырыптар бойынша көп
 - mmlu-translated-kk
 - kazakh-constitution-mc
 - kazakh-dastur-mc
-- kazakh-unified-national-testing-mc
+- kazakh-unified-national-testing-mc(biology,english, geography, history of kz, world's history, society rights, literature, kazakh language)
 
 Әр тапсырмада 4-8 жауап нұсқасы бар.
 
@@ -63,21 +57,15 @@ Kaz LLM – бұл төмендегі тақырыптар бойынша көп
 ### Орнату
 Қажетті кітапхананы орнату үшін төмендегі команданы орындаңыз:
 ```bash
-git clone --depth 1 https://github.com/horde-research/lm-evaluation-harness-kk.git
-cd lm-evaluation-harness-kk
-pip install -e .
+git clone https://github.com/horde-research/horde-common.git
+cd scripts
+pip install -r requirements.txt
 ```
 
 ### Орындау
 Бенчмаркті іске қосу үшін келесі команданы пайдаланыңыз:
 ```bash
-lm_eval \
-    --model hf \
-    --model_args pretrained={hf/model} \
-    --batch_size 8 \
-    --num_fewshot 0 \
-    --tasks mmlu_translated_kk,kazakh_and_literature_unt_mc,kk_biology_unt_mc,kk_constitution_mc,kk_dastur_mc,kk_english_unt_mc,kk_geography_unt_mc,kk_history_of_kazakhstan_unt_mc,kk_human_society_rights_unt_mc,kk_unified_national_testing_mc,kk_world_history_unt_mc \
-    --output output
+python mc-eval-simplified-inference.py --model_id deepseek-ai/DeepSeek-R1-Distill-Qwen-14B --output_path .
 ```
 
 ### Нәтижелер