Update README.md

README.md

@@ -61,8 +61,7 @@ Here's how you can run the model using the `pipeline()` function from 🤗 Trans
 import torch
 from transformers import pipeline
 
-pipe = pipeline(“text-generation”, model=“Unbabel/TowerInstruct-v0.1", torch_dtype=torch.bfloat16, device_map=“cuda:3”)
-
+pipe = pipeline(“text-generation”, model=“Unbabel/TowerInstruct-v0.1“, torch_dtype=torch.bfloat16, device_map=“auto”)
 # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
 messages = [
     {“role”: “user”, “content”: “Translate the following text from Portuguese into English.\nPortuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.\nEnglish:“},
@@ -78,37 +77,48 @@ print(outputs[0][“generated_text”])
 # A group of researchers has launched a new model for translation-related tasks.
 ```
 
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+The model is not guaranteed to perform for languages other than the 10 languages it supports. Even though we trained the model on conversational data and code instructions, it is not intended to be used as a conversational chatbot or code assistant.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+TowerInstruct-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).  
 
 ## Prompt Format
 
-Mention mlchat here (no system prompt)
+TowerInstruct-v0.1 was trained using the ChatML prompt templates without any system prompts. An example follows below:
+```
+<|im_start|>user
+{USER PROMPT}<|im_end|>
+<|im_start|>assistant
+{MODEL RESPONSE}<|im_end|>
+<|im_start|>user
+[...]
+```
 
 ### Supervised tasks
 
-Prompts for different tasks.
-
+- Translation
+```
+Translate the following text from $SRC_LANG into $TGT_LANG.
+$SRC_LANG: $SRC_TEXT
+$TGT_LANG: # make sure to add a white space the target placeholder "$TGT_LANG:" for best results
+```
+- Automatic Post Edition
+```
+Translate the following text from $SRC_LANG into $TGT_LANG.
+$SRC_LANG: $SRC_TEXT
+$TGT_LANG: 
+```
+- Machine Translation Evaluation
+- Context-aware Translation
+- Terminology-aware Translation
+- Multi-reference Translation
+- Named-entity Recognition
+- Paraphrase Generation
+- Synthetic Chat data 
+- Code instructions
 [More Information Needed]
 
 ## Training Details
@@ -125,17 +135,21 @@ Write sth about Axolotl.
 
 The following hyperparameters were used during training:
 
-learning_rate: 7e-06
-seed: 42
-distributed_type: multi-GPU
-num_devices: 4
-total_train_batch_size: 256
-optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-lr_scheduler_type: cosine
-lr_scheduler_warmup_steps: 500
-weight_decay: 0.01
-num_epochs: 4
-max_seq_length: 2048
+- total_train_batch_size: 256
+
+- learning_rate: 7e-06
+
+- lr_scheduler_type: cosine
+
+- lr_scheduler_warmup_steps: 500
+
+- weight_decay: 0.01
+
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+
+- num_epochs: 4
+
+- max_seq_length: 2048
 
 ## Citation