ruwan commited on
Commit
d357fd9
·
1 Parent(s): 9f2101a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -1,3 +1,14 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+ note : use original open llama tokenizer
5
+
6
+ #model_path = 'openlm-research/open_llama_3b'
7
+ model_path = 'ruwan/open-llama-sharded-1GB-7B-alpaca-vmware'
8
+ # model_path = 'openlm-research/open_llama_13b_600bt'
9
+
10
+ tokenizer = LlamaTokenizer.from_pretrained("openlm-research/open_llama_7b")
11
+ model = LlamaForCausalLM.from_pretrained(
12
+ model_path, torch_dtype=torch.float16, device_map='auto',load_in_8bit=True
13
+ )
14
+