Improve LLM Backbone Explanations

documentation/docs/guide/experiments/create-an-experiment.md

@@ -16,7 +16,7 @@ Follow the relevant steps below to create an experiment in H2O LLM Studio.
 4. Provide a meaningful **Experiment name**.
 
 5. Define the parameters. The most important parameters are:
-    - **LLM Backbone**: This parameter determines the LLM architecture to use. It is the foundation model that you continue training. H2O LLM Studio has a predefined list of recommended types of foundation models, but you can also use [Hugging Face models](https://huggingface.co/models).
+    - **LLM Backbone**: This parameter determines the LLM architecture to use. It is the foundation model that you continue training. H2O LLM Studio has a predefined list of recommended foundation models available in the dropdown list. You can also type in the name of a [Hugging Face model](https://huggingface.co/models) that is not in the list, for example: `h2oai/h2o-danube2-1.8b-sft` or the path of a local folder that has the model you would like to fine-tune.
     - **Mask Prompt Labels**: This option controls whether to mask the prompt labels during training and only train on the loss of the answer.
     - Hyperparameters such as **Learning rate**, **Batch size**, and number of epochs determine the training process. You can refer to the tooltips that are shown next to each hyperparameter in the GUI to learn more about them.
     - **Evaluate Before Training**: This option lets you evaluate the model before training, which can help you judge the quality of the LLM backbone before fine-tuning. 

documentation/docs/guide/experiments/export-trained-model.md

@@ -23,7 +23,7 @@ To publish a trained model to Hugging Face Hub:
 
 6. Click **Export**.
 
-    ![export model to hugging face](export-model-to-huggingface.png)
+    ![export model to Hugging Face](export-model-to-huggingface.png)
 
 ## Download a model
 
@@ -34,7 +34,7 @@ Use the following code snippet to utilize the converted model in Jupyter Noteboo
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "path_to_downloaded_model"  # either local folder or huggingface model name
+model_name = "path_to_downloaded_model"  # either local folder or Hugging Face model name
 
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.

documentation/docs/tooltips/experiments/_llm-backbone.mdx

@@ -1,5 +1,5 @@
 The **LLM Backbone** option is the most important setting as it sets the pretrained model weights.
 
-- Usually, it is good to use smaller architectures for quicker experiments and larger models when aiming for the highest accuracy
-- If possible, leverage backbones pre-trained closely to your use case
-- Any huggingface model can be used here (not limited to the ones in the dropdown list)
+- Use smaller models for quicker experiments and larger models for higher accuracy
+- Aim to leverage models pre-trained on tasks similar to your use case when possible
+- Select a model from the dropdown list or type in the name of a Hugging Face model of your preference

model_cards/text_causal_classification_experiment_summary_card_template.md

@@ -20,7 +20,7 @@ You will also need to download the classification head, either manually, or by r
 ```python
 from huggingface_hub import hf_hub_download
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 hf_hub_download(repo_id=model_name, filename="classification_head.pth", local_dir="./")
 ```
 
@@ -29,7 +29,7 @@ You can make classification predictions by following the example below:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "{{text_prompt_start}}How are you?{{end_of_sentence}}{{text_answer_separator}}"

model_cards/text_causal_classification_model_card_template.md

@@ -37,7 +37,7 @@ You will also need to download the classification head, either manually, or by r
 ```python
 from huggingface_hub import hf_hub_download
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 hf_hub_download(repo_id=model_name, filename="classification_head.pth", local_dir="./")
 ```
 
@@ -46,7 +46,7 @@ You can make classification predictions by following the example below:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "{{text_prompt_start}}How are you?{{end_of_sentence}}{{text_answer_separator}}"

model_cards/text_causal_language_modeling_model_card_template.md

@@ -79,7 +79,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 messages = {{sample_messages}}

model_cards/text_sequence_to_sequence_modeling_experiment_summary_card_template.md

@@ -13,7 +13,7 @@ pip install transformers=={{transformers_version}}
 ```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "{{text_prompt_start}}How are you?{{end_of_sentence}}{{text_answer_separator}}"

model_cards/text_sequence_to_sequence_modeling_model_card_template.md

@@ -32,7 +32,7 @@ For inference, you can use the following code snippet:
 ```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-model_name = "{{repo_id}}"  # either local folder or huggingface model name
+model_name = "{{repo_id}}"  # either local folder or Hugging Face model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "{{text_prompt_start}}How are you?{{end_of_sentence}}{{text_answer_separator}}"