muzerai commited on
Commit
7a04f2e
·
verified ·
1 Parent(s): caa6234

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  - merge
9
 
10
  ---
11
- # Llama-3.1-Ko-8B-magic8
12
 
13
  The merged model combining Llama-3.1-Korean-8B-Instruct and Llama-3.1-Storm-8B improves performance like — including Korean-language instruction following, multilingual knowledge-based QA, reasoning, reduced hallucinations, and structured output generation (e.g., JSON, Markdown). This merge is particularly beneficial for developers seeking a strong Korean-capable model that also excels in logic, accuracy, and function-calling, while remaining lightweight enough for local inference environments such as Ollama or vLLM.
14
 
 
8
  - merge
9
 
10
  ---
11
+ # Llama-3.1-Ko-8B-magic8 made by "AIJOAH"
12
 
13
  The merged model combining Llama-3.1-Korean-8B-Instruct and Llama-3.1-Storm-8B improves performance like — including Korean-language instruction following, multilingual knowledge-based QA, reasoning, reduced hallucinations, and structured output generation (e.g., JSON, Markdown). This merge is particularly beneficial for developers seeking a strong Korean-capable model that also excels in logic, accuracy, and function-calling, while remaining lightweight enough for local inference environments such as Ollama or vLLM.
14