Hugging Face's logo

legenduck
/
llama-3-Korean-Bllossom-70B-GGUF

Text Generation
GGUF
English
Korean
Inference Endpoints
conversational
Model card Files Community
legenduck commited on
Commit
dd37699
·
verified ·
1 Parent(s): f79f806

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -5,8 +5,11 @@ language:
5
  - ko
6
  base_model:
7
  - Bllossom/llama-3-Korean-Bllossom-70B
 
 
8
  ---
 
9
 
10
- Using llama.cpp release b3972 for quantization.
11
 
12
  Original model: https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B
 
5
  - ko
6
  base_model:
7
  - Bllossom/llama-3-Korean-Bllossom-70B
8
+ pipeline_tag: text-generation
9
+ quantized_by: legenduck
10
  ---
11
+ ## Llamacpp Quantizations of llama-3-Korean-Bllossom-70B(Aiming for around 40GB)
12
 
13
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4048">b4048</a> for quantization.
14
 
15
  Original model: https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B