sebaxakerhtc commited on
Commit
32343ba
·
verified ·
1 Parent(s): c81941b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -8
README.md CHANGED
@@ -5,14 +5,14 @@ tags:
5
  - transformers
6
  - unsloth
7
  - sebaxakerhtc
8
- - bggpt
9
  - llama
10
- - trl
11
  license: apache-2.0
12
  language:
13
- - bg
14
  datasets:
15
- - burgasdotpro/synthetic_dataset
16
  ---
17
 
18
  # Uploaded model
@@ -21,9 +21,8 @@ datasets:
21
  - **License:** apache-2.0
22
  - **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit
23
 
24
- Първите резултати, които не са лоши...
25
- Засега е тренирана върху моят малък датасет с 1000 реда синтетически дани (формат: въпрос-отговор)
26
 
27
- Тази llama модела тренирана 2 пъти по-бързо с помоща на [Unsloth](https://github.com/unslothai/unsloth) и TRL библиотеката на Huggingface.
28
 
29
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="100"/>](https://github.com/unslothai/unsloth)
 
5
  - transformers
6
  - unsloth
7
  - sebaxakerhtc
8
+ - saiga
9
  - llama
10
+ - gguf
11
  license: apache-2.0
12
  language:
13
+ - ru
14
  datasets:
15
+ - IlyaGusev/saiga_scored
16
  ---
17
 
18
  # Uploaded model
 
21
  - **License:** apache-2.0
22
  - **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit
23
 
24
+ Тестовая модель на базе llama-3.1-8B с датасетом от знаменитой [Сайги](https://huggingface.co/IlyaGusev/saiga_llama3_8b).
 
25
 
26
+ Эта {model_type} модель тренирована в 2 раза быстрей с помощью [Unsloth](https://github.com/unslothai/unsloth) и TRL библиотеки Huggingface
27
 
28
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="100"/>](https://github.com/unslothai/unsloth)