Hugging Face's logo

royleibov
/
Jamba-v0.1-ZipNN-Compressed

Text Generation
Transformers
Safetensors
jamba
mamba
Mixture of Experts
custom_code
Inference Endpoints
Model card Files Community
royleibov commited on
Commit
d5966db
·
verified ·
1 Parent(s): ef9dc41

remove trust remote code

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -26,7 +26,7 @@ from zipnn import zipnn_hf
26
 
27
  zipnn_hf()
28
 
29
- pipe = pipeline("text-generation", model="royleibov/Jamba-v0.1-ZipNN-Compressed", trust_remote_code=True)
30
  ```
31
  ```python
32
  # Load model directly
@@ -35,8 +35,8 @@ from zipnn import zipnn_hf
35
 
36
  zipnn_hf()
37
 
38
- tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed", trust_remote_code=True)
39
- model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed", trust_remote_code=True)
40
  ```
41
  ### ZipNN
42
  ZipNN also allows you to seemlessly save local disk space in your cache after the model is downloaded.
 
26
 
27
  zipnn_hf()
28
 
29
+ pipe = pipeline("text-generation", model="royleibov/Jamba-v0.1-ZipNN-Compressed")
30
  ```
31
  ```python
32
  # Load model directly
 
35
 
36
  zipnn_hf()
37
 
38
+ tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
39
+ model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
40
  ```
41
  ### ZipNN
42
  ZipNN also allows you to seemlessly save local disk space in your cache after the model is downloaded.