Update README.md

README.md

@@ -61,21 +61,21 @@ 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="auto")
+pipe = pipeline(“text-generation”, model=“Unbabel/TowerInstruct-v0.1", torch_dtype=torch.bfloat16, device_map=“cuda:3”)
 
-# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+# 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 English into Portuguese.\nEnglish: A group of researchers has released a new model for translation-related tasks.\nPortuguese:"},
+    {“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:“},
 ]
 prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
-print(outputs[0]["generated_text"])
-# <|system|>
-# You are a friendly chatbot who always responds in the style of a pirate.</s>
-# <|user|>
-# How many helicopters can a human eat in one sitting?</s>
-# <|assistant|>
-# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
+print(outputs[0][“generated_text”])
+# <|im_start|>user
+# Translate the following text from Portuguese into English.
+# Portuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.
+# English:<|im_end|>
+# <|im_start|>assistant
+# A group of researchers has launched a new model for translation-related tasks.
 ```
 
 
@@ -125,18 +125,17 @@ Write sth about Axolotl.
 
 The following hyperparameters were used during training:
 
-learning_rate: 5e-07
-train_batch_size: 2
-eval_batch_size: 4
+learning_rate: 7e-06
 seed: 42
 distributed_type: multi-GPU
-num_devices: 16
-total_train_batch_size: 32
-total_eval_batch_size: 64
+num_devices: 4
+total_train_batch_size: 256
 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-lr_scheduler_type: linear
-lr_scheduler_warmup_ratio: 0.1
-num_epochs: 3.0
+lr_scheduler_type: cosine
+lr_scheduler_warmup_steps: 500
+weight_decay: 0.01
+num_epochs: 4
+max_seq_length: 2048
 
 ## Citation