Update lora.md (typos)

docs/source/developer_guides/lora.md

@@ -9,7 +9,7 @@ Unless required by applicable law or agreed to in writing, software distributed
 an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
 specific language governing permissions and limitations under the License.
 
-⚠️ Note that this file is in Markdown but contain specific syntax for our doc-builder (similar to MDX) that may not be
+⚠️ Note that this file is in Markdown but contains specific syntax for our doc-builder (similar to MDX) that may not be
 rendered properly in your Markdown viewer.
 
 -->
@@ -71,7 +71,7 @@ When quantizing the base model for QLoRA training, consider using the [LoftQ ini
 
 In general, for LoftQ to work best, it is recommended to target as many layers with LoRA as possible, since those not targeted cannot have LoftQ applied. This means that passing `LoraConfig(..., target_modules="all-linear")` will most likely give the best results. Also, you should use `nf4` as quant type in your quantization config when using 4bit quantization, i.e. `BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4")`.
 
-#### A more convienient way
+#### A more convenient way
 
 An easier but more limited way to apply LoftQ initialization is to use the convenience function `replace_lora_weights_loftq`. This takes the quantized PEFT model as input and replaces the LoRA weights in-place with their LoftQ-initialized counterparts.
 
@@ -140,7 +140,7 @@ model = PeftModel.from_pretrained(base_model, peft_model_id, ephemeral_gpu_offlo
 
 #### Caveats
 
-- DoRA only supports linear and Conv2d layers at the momement.
+- DoRA only supports linear and Conv2d layers at the moment.
 - DoRA introduces a bigger overhead than pure LoRA, so it is recommended to merge weights for inference, see [`LoraModel.merge_and_unload`]. 
 - DoRA should work with weights quantized with bitsandbytes ("QDoRA"). However, issues have been reported when using QDoRA with DeepSpeed Zero2.
 
@@ -160,7 +160,7 @@ An approach used to improve the performance of models is to expand a model by du
 config = LoraConfig(layer_replication=[[0,4], [2,5]], ...)
 ```
 
-Assuming the original model had 5 layers `[0, 1, 2 ,3, 4]`, this would create a model with 7 layers arranged as `[0, 1, 2, 3, 2, 3, 4]`. This follows the [mergekit](https://github.com/arcee-ai/mergekit) pass through merge convention where sequences of layers specified as start inclusive and end exclusive tuples are stacked to build the final model. Each layer in the final model gets its own distinct set of LoRA adpaters.
+Assuming the original model had 5 layers `[0, 1, 2 ,3, 4]`, this would create a model with 7 layers arranged as `[0, 1, 2, 3, 2, 3, 4]`. This follows the [mergekit](https://github.com/arcee-ai/mergekit) pass through merge convention where sequences of layers specified as start inclusive and end exclusive tuples are stacked to build the final model. Each layer in the final model gets its own distinct set of LoRA adapters.
 
 [Fewshot-Metamath-OrcaVicuna-Mistral-10B](https://huggingface.co/abacusai/Fewshot-Metamath-OrcaVicuna-Mistral-10B) is an example of a model trained using this method on Mistral-7B expanded to 10B. The
 [adapter_config.json](https://huggingface.co/abacusai/Fewshot-Metamath-OrcaVicuna-Mistral-10B/blob/main/adapter_config.json) shows a sample LoRA adapter config applying this method for fine-tuning.
@@ -324,7 +324,7 @@ model.delete_adapter("dpo")
 
 Normally, each inference batch has to use the same adapter(s) in PEFT. This can sometimes be annoying, because we may have batches that contain samples intended to be used with different LoRA adapters. For example, we could have a base model that works well in English and two more LoRA adapters, one for French and one for German. Usually, we would have to split our batches such that each batch only contains samples of one of the languages, we cannot combine different languages in the same batch.
 
-Thankfully, it is possible to mix different LoRA adapters in the same batch using the `adapter_name` argument. Below, we show an examle of how this works in practice. First, let's load the base model, English, and the two adapters, French and German, like this:
+Thankfully, it is possible to mix different LoRA adapters in the same batch using the `adapter_name` argument. Below, we show an example of how this works in practice. First, let's load the base model, English, and the two adapters, French and German, like this:
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM