Update README.md

README.md

@@ -76,7 +76,7 @@ Use the code below to get started with the model.
 
 ```python
 model_name = 'msc-smart-contract-auditing/deepseek-coder-6.7b-vulnerability'
-tokenizer = AutoTokenizer.from_pretrained( # For some reason the tokenizer didn't safe properly
+tokenizer = AutoTokenizer.from_pretrained( # For some reason the tokenizer didn't save properly
     "deepseek-ai/deepseek-coder-6.7b-instruct", 
     trust_remote_code=True, 
     force_download=True,
@@ -118,34 +118,25 @@ https://huggingface.co/datasets/msc-smart-contract-auditing/audits-with-reasons
 ### Training Procedure
 
 lora_config = LoraConfig(
-    r=16,  # rank
-    lora_alpha=32,  # scaling factor
-    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj",],
-    lora_dropout=0.05,  # dropout rate for LoRA layers
+  r=16,  # rank
+  lora_alpha=32,  # scaling factor
+  target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj",],
+  lora_dropout=0.05,  # dropout rate for LoRA layers
 )
 
-model = get_peft_model(model, lora_config)
-
-from transformers import Trainer, TrainingArguments
-
-trainer = Trainer(
-    model=model,
-    args=TrainingArguments(
-        per_device_train_batch_size = 2,
-        gradient_accumulation_steps = 4,
-        warmup_steps = 5,
-        num_train_epochs = 1,
-        learning_rate = 2e-4,
-        fp16 = True,
-        logging_steps = 1,
-        optim = "adamw_8bit",
-        weight_decay = 0.01,
-        lr_scheduler_type = "linear",
-        seed = 3407,
-        output_dir = "outputs",
-    ),
-    train_dataset=train_prompts,
-    eval_dataset=test_prompts,
+TrainingArguments(
+  per_device_train_batch_size = 2,
+  gradient_accumulation_steps = 4,
+  warmup_steps = 5,
+  num_train_epochs = 1,
+  learning_rate = 2e-4,
+  fp16 = True,
+  logging_steps = 1,
+  optim = "adamw_8bit",
+  weight_decay = 0.01,
+  lr_scheduler_type = "linear",
+  seed = 3407,
+  output_dir = "outputs",
 )
 
 #### Training Hyperparameters
@@ -160,81 +151,6 @@ trainer = Trainer(
 
 https://huggingface.co/datasets/msc-smart-contract-auditing/audits-with-reasons
 
-#### Factors
-
-[More Information Needed]
-
-#### Metrics
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
 ### Framework versions
 
 - PEFT 0.11.1