Archives/petals
2
0
Fork 0
mirror of https://github.com/bigscience-workshop/petals synced 2024-11-10 01:10:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Hide excess key message (#476)

Browse Source 
Before:

```python
Aug 23 23:51:31.394 [INFO] Loaded Maykeye/TinyLLama-v0 block 0, _IncompatibleKeys(missing_keys=[], unexpected_keys=['self_attn.rotary_emb.inv_freq'])
```

After:

```python
Aug 23 23:51:31.394 [INFO] Loaded Maykeye/TinyLLama-v0 block 0
```

Hiding this since the excess keys in Llama-based models are okay since the latest transformers release.
This commit is contained in:
Alexander Borzunov 2023-08-24 00:41:40 +04:00 committed by GitHub
parent a14ae7334d
commit df8ab09ca2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/petals/server/from_pretrained.py
View File

@ -74,7 +74,8 @@ def load_pretrained_block(
param = param.to(torch_dtype) param = param.to(torch_dtype)
set_module_tensor_to_device(block, param_name, "cpu", value=param, dtype=param.dtype) set_module_tensor_to_device(block, param_name, "cpu", value=param, dtype=param.dtype)
logger.info(f"Loaded {model_name} block {block_index}, {report}") logger.info(f"Loaded {model_name} block {block_index}")
logger.debug(f"Details: {report}")
return block return block