SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

LLaMA house-keeping (#22216)

Browse Source 
* LLaMA house-keeping

* Doc links
This commit is contained in:
Sylvain Gugger
2023-03-17 08:55:15 -04:00
committed by GitHub
parent 42f8f76402
commit 00934026a4
3 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/en/model_doc/llama.mdx
View File

@@ -33,8 +33,10 @@ python src/transformers/models/llama/convert_llama_weights_to_hf.py \
- After conversion, the model and tokenizer can be loaded via:
```python
tokenizer = transformers.LlamaTokenizer.from_pretrained("/output/path/tokenizer/")
model = transformers.LlamaForCausalLM.from_pretrained("/output/path/llama-7b/")
from transformers import LlamaForCausalLM, LlamaTokenizer
tokenizer = LlamaTokenizer.from_pretrained("/output/path/tokenizer/")
model = LlamaForCausalLM.from_pretrained("/output/path/llama-7b/")
```
- The LLaMA tokenizer is based on [sentencepiece](https://github.com/google/sentencepiece). One quirk of sentencepiece is that when decoding a sequence, if the first token is the start of the word (e.g. "Banana"), the tokenizer does not prepend the prefix space to the string. To have the tokenizer output the prefix space, set `decode_with_prefix_space=True` in the `LlamaTokenizer` object or in the tokenizer configuration.