Fix minor typo

#45
by pcuenq HF staff - opened
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -163,7 +163,7 @@ Falcon-7B is a causal decoder-only model trained on a causal language modeling t
163
 
164
  The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences:
165
 
166
- * **Positionnal embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864));
167
  * **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135));
168
  * **Decoder-block:** parallel attention/MLP with a single layer norm.
169
 
 
163
 
164
  The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences:
165
 
166
+ * **Positional embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864));
167
  * **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135));
168
  * **Decoder-block:** parallel attention/MLP with a single layer norm.
169