Thaweewat commited on
Commit
8c5c1c4
β€’
1 Parent(s): 24eec99

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -15,10 +15,10 @@ datasets:
15
 
16
  # πŸƒπŸ‡ΉπŸ‡­ Buffala-LoRa-TH
17
 
18
- Buffala-LoRA is a 7B-parameter LLaMA model finetuned to follow instructions. It is trained on the Stanford Alpaca (TH), WikiTH, Pantip and IAppQ&A dataset and makes use of the Huggingface LLaMA implementation. For more information, please visit [the project's website](https://github.com/tloen/alpaca-lora).
19
 
20
  ## Issues and what next?
21
- - The model still lacks a significant amount of world knowledge, so it is necessary to fine-tune it on larger Thai datasets > Next version: CCNet,OSCAR,Wiki (TH)
22
  - Currently, there is no translation prompt. We plan to fine-tune the model on the SCB Thai-English dataset soon.
23
  - The model works well with the LangChain Search agent (Serpapi), which serves as a hotfix for world knowledge. > Plan for Spaces with search chain demo
24
  - Lacked of chat capabilities, waiting for LangChain implementation.
 
15
 
16
  # πŸƒπŸ‡ΉπŸ‡­ Buffala-LoRa-TH
17
 
18
+ Buffala-LoRA is a 7B-parameter LLaMA model finetuned to follow instructions. It is trained on the Stanford Alpaca (TH Translated), WikiTH, Pantip and IAppQ&A dataset and makes use of the Huggingface LLaMA implementation. For more information, please visit [the project's website](https://github.com/tloen/alpaca-lora).
19
 
20
  ## Issues and what next?
21
+ - The model still lacks a significant amount of world knowledge, so it is necessary to fine-tune it on larger Thai datasets > Next version: CCNet,OSCAR,thWiki
22
  - Currently, there is no translation prompt. We plan to fine-tune the model on the SCB Thai-English dataset soon.
23
  - The model works well with the LangChain Search agent (Serpapi), which serves as a hotfix for world knowledge. > Plan for Spaces with search chain demo
24
  - Lacked of chat capabilities, waiting for LangChain implementation.