Hugging Face's logo

mikeriess
/
Llama-3.1-Nemotron-70B-Reward-HF-INT4

Safetensors
llama
4-bit precision
bitsandbytes
Model card Files Community
mikeriess commited on
Commit
62c0c9b
·
verified ·
1 Parent(s): 7f9ac6a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -1,7 +1,11 @@
1
  ---
2
  license: llama3.1
3
  ---
4
- 4-bit version of the origninal model by Meta+Nvidia. This consumes about 52 GB VRAM.
 
 
 
 
5
 
6
  Please refer to the original license:
7
  https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward-HF
 
1
  ---
2
  license: llama3.1
3
  ---
4
+
5
+ # Llama-3.1-Nemotron-70B-Reward-HF-INT4
6
+ 4-bit version of the origninal model by Meta+Nvidia.
7
+
8
+ This consumes about 52 GB VRAM.
9
 
10
  Please refer to the original license:
11
  https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward-HF