AELLM commited on
Commit
bc85954
·
verified ·
1 Parent(s): f238eba

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -28,7 +28,7 @@ tags:
28
  The importance of a small parameter large language model (LLM) lies in its ability to balance performance and efficiency. As LLMs grow increasingly sophisticated, the trade-off between model size and computational resource demands becomes critical. A smaller parameter model offers significant advantages, such as reduced memory usage, faster inference times, and lower energy consumption, all while retaining a high level of accuracy and contextual understanding. These models are particularly valuable in real-world applications where resources like processing power and storage are limited, such as on mobile devices, edge computing, or low-latency environments.
29
 
30
  ## Llama 3.2 Chibi 3B
31
- This experimental model is the result from continual pre-training of [Meta's Llama 3.2 3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on a small mixture of japanese datasets.
32
 
33
  ## Architecture
34
  [Llama 3.2 3B](https://huggingface.co/meta-llama/Llama-3.2-3B)
 
28
  The importance of a small parameter large language model (LLM) lies in its ability to balance performance and efficiency. As LLMs grow increasingly sophisticated, the trade-off between model size and computational resource demands becomes critical. A smaller parameter model offers significant advantages, such as reduced memory usage, faster inference times, and lower energy consumption, all while retaining a high level of accuracy and contextual understanding. These models are particularly valuable in real-world applications where resources like processing power and storage are limited, such as on mobile devices, edge computing, or low-latency environments.
29
 
30
  ## Llama 3.2 Chibi 3B
31
+ This experimental model is a result from continual pre-training of [Meta's Llama 3.2 3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on a small mixture of japanese datasets.
32
 
33
  ## Architecture
34
  [Llama 3.2 3B](https://huggingface.co/meta-llama/Llama-3.2-3B)