Nanobit commited on
Commit
68237ea
1 Parent(s): 4ee79f2

Add extra note to Readme

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -55,6 +55,7 @@ See sample configs in [configs](configs) folder. It is recommended to duplicate
55
  ```yaml
56
  base_model: ./llama-7b-hf # local or huggingface repo
57
  ```
 
58
 
59
  - dataset
60
  ```yaml
@@ -71,6 +72,7 @@ See sample configs in [configs](configs) folder. It is recommended to duplicate
71
  fp16: true
72
  tf32: true
73
  ```
 
74
 
75
  - lora
76
  ```yaml
 
55
  ```yaml
56
  base_model: ./llama-7b-hf # local or huggingface repo
57
  ```
58
+ Note: The code will load the right architecture.
59
 
60
  - dataset
61
  ```yaml
 
72
  fp16: true
73
  tf32: true
74
  ```
75
+ Note: Repo does not do 4-bit quantization.
76
 
77
  - lora
78
  ```yaml