georgebu
/

ppo_model

@@ -1,199 +1,52 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### 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.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## 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]

 ---
 library_name: transformers
+datasets:
+- HumanLLMs/Human-Like-DPO-Dataset
+language:
+- en
+base_model:
+- HuggingFaceTB/SmolLM-135M-Instruct
 ---
+## Описание модели
+В рамках домашнего задания по курсу "Современный NLP. Большие языковые модели" от vk.education было реализовано дообучение модели методом Proximal Policy Optimization (PPO)
+## Как использовать:
+``` python
+tokenizer = AutoTokenizer.from_pretrained('georgebu/llm-course-hw2-ppo')
+dpo_model = AutoModelForCausalLM.from_pretrained(georgebu/llm-course-hw2-ppo)
+messages = [{"role": "user", "content": "What kind of sport do you like"}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+generated_ids = dpo_model.generate(model_inputs.input_ids, max_new_tokens=256, do_sample=False)
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+## Примеры генерации:
+<div style="
+    background: #1a2639;
+    padding: 14px;
+    border-radius: 6px;
+    border-left: 3px solid #3a86ff;
+    color: #e0e0e0;
+    font-family: 'Consolas', monospace;
+    margin: 16px 0;
+">
+<b>Промт:</b> "What is your morning routine like?"
+<b>Ответ модели:</b>
+Proximal Policy Optimization (PPO) is a subfield of Machine Learning that focuses on designing the policies that reduce the variance of a neural network's performance by minimizing the reconstruction loss. The goal of PPO is to identify the optimal policy that reduces the variance while encouraging the model to be more accurate and robust to noise.
+In a traditional neural network, the model tries to achieve a good approximation from the training data. However, the model is often biased towards the lower-bounds of the approximation, leading to a high loss in the vicinity of the true values, even when the network estimates the true values as smooth. This is called the "inference problem."
+PPO addresses this problem by learning a policy that is designed to take the true values of the data and infer the behavior of the network. The goal is to design a policy that assigns a high probability to the network's correct output, while minimizing the mispredictions. This is a relatively simple problem compared to the true-to-true ratio, and many popular optimization algorithms, such as gradient descent and Adam, are specifically designed to take the true values (called "global minimum" in the context of PPO) as a function of the network's parameters.
+PPO provides a more robust and efficient implementation than traditional batch-distributed neural networks (BDN), which is a more complex and computationally expensive approach. In a BDN, the model is optimized for a specific task or environment, such as a regression task, and the network is trained to learn a suitable policy that minimizes the performance loss. In contrast, PPO designs the network to adaptively learn a more promising policy when a certain misclassification error occurs, rather than solely optimizing the final value of the network.
+</div>
+## Баги:
+Иногда модель "сходит с ума" и начинает генерировать один и тот же заученный текст про функции на Python. Во избежание этого рекомендуется прописать этот текст в negative_prompt