kz-transformers commited on
Commit
3ba8bcb
·
verified ·
1 Parent(s): a727e34

Update src/display/about.py

Browse files
Files changed (1) hide show
  1. src/display/about.py +18 -12
src/display/about.py CHANGED
@@ -27,18 +27,21 @@ Each task contains from 4 to 8 answer choices.
27
  ### Installation
28
  To install the necessary library, run the following command:
29
  ```bash
30
- pip install git+https://github.com/horde-research/kaz-llm-eval-lb.git --upgrade --force-reinstall --no-deps
 
 
 
 
31
  ```
32
  ### Execution
33
  To run the benchmark, use the following command:
34
  ```bash
35
- !lm_eval \
36
  --model hf \
37
- --model_args pretrained={hf/model},dtype=float16 \
38
- --batch_size 1 \
39
- --apply_chat_template \
40
  --num_fewshot 0 \
41
- --tasks kazakh-dastur-mc \
42
  --output output
43
  ```
44
  ### Results
@@ -62,19 +65,22 @@ Kaz LLM – бұл төмендегі тақырыптар бойынша көп
62
  ### Орнату
63
  Қажетті кітапхананы орнату үшін төмендегі команданы орындаңыз:
64
  ```bash
65
- pip install git+https://github.com/horde-research/kaz-llm-eval-lb.git --upgrade --force-reinstall --no-deps
 
 
 
 
66
  ```
67
 
68
  ### Орындау
69
  Бенчмаркті іске қосу үшін келесі команданы пайдаланыңыз:
70
  ```bash
71
- !lm_eval \
72
  --model hf \
73
- --model_args pretrained={hf/model},dtype=float16 \
74
- --batch_size 1 \
75
- --apply_chat_template \
76
  --num_fewshot 0 \
77
- --tasks kazakh-dastur-mc \
78
  --output output
79
  ```
80
 
 
27
  ### Installation
28
  To install the necessary library, run the following command:
29
  ```bash
30
+ git clone --depth 1 https://github.com/horde-research/lm-evaluation-harness-kk.git
31
+ cd lm-evaluation-harness-kk
32
+ python3 -m venv .venv
33
+ source .venv/bin/activate
34
+ pip install -e .
35
  ```
36
  ### Execution
37
  To run the benchmark, use the following command:
38
  ```bash
39
+ lm_eval \
40
  --model hf \
41
+ --model_args pretrained={hf/model} \
42
+ --batch_size 8 \
 
43
  --num_fewshot 0 \
44
+ --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 \
45
  --output output
46
  ```
47
  ### Results
 
65
  ### Орнату
66
  Қажетті кітапхананы орнату үшін төмендегі команданы орындаңыз:
67
  ```bash
68
+ git clone --depth 1 https://github.com/horde-research/lm-evaluation-harness-kk.git
69
+ cd lm-evaluation-harness-kk
70
+ python3 -m venv .venv
71
+ source .venv/bin/activate
72
+ pip install -e .
73
  ```
74
 
75
  ### Орындау
76
  Бенчмаркті іске қосу үшін келесі команданы пайдаланыңыз:
77
  ```bash
78
+ lm_eval \
79
  --model hf \
80
+ --model_args pretrained={hf/model} \
81
+ --batch_size 8 \
 
82
  --num_fewshot 0 \
83
+ --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 \
84
  --output output
85
  ```
86