Hugging Face's logo

Hazan-Lab
/
Transformer_500M

Safetensors
minitransformer
Model card Files
xet
Community
yagizdevre commited on
Commit
ca03f9d
·
1 Parent(s): 56f9050

naming fix

Browse files
Files changed (4) hide show
  1. __pycache__/attn.cpython-312.pyc +0 -0
  2. __pycache__/configuration_minitransformer.cpython-312.pyc +0 -0
  3. __pycache__/modeling_minitransformer.cpython-312.pyc +0 -0
  4. config.json +1 -1
__pycache__/attn.cpython-312.pyc CHANGED
Binary files a/__pycache__/attn.cpython-312.pyc and b/__pycache__/attn.cpython-312.pyc differ
 
__pycache__/configuration_minitransformer.cpython-312.pyc CHANGED
Binary files a/__pycache__/configuration_minitransformer.cpython-312.pyc and b/__pycache__/configuration_minitransformer.cpython-312.pyc differ
 
__pycache__/modeling_minitransformer.cpython-312.pyc CHANGED
Binary files a/__pycache__/modeling_minitransformer.cpython-312.pyc and b/__pycache__/modeling_minitransformer.cpython-312.pyc differ
 
config.json CHANGED
@@ -3,7 +3,7 @@
3
  "_name_or_path": "Transformer_500M",
4
  "architectures": ["MiniTransformer"],
5
  "n_embd": 768,
6
- "n_heads": 24,
7
  "n_layers": 27,
8
  "seq_len": 8192,
9
  "window_size": 8192,
 
3
  "_name_or_path": "Transformer_500M",
4
  "architectures": ["MiniTransformer"],
5
  "n_embd": 768,
6
+ "n_heads": 12,
7
  "n_layers": 27,
8
  "seq_len": 8192,
9
  "window_size": 8192,