mcnckc
/

llm-hw2-dpo

@@ -1,199 +1,65 @@
 ---
 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
+pipeline_tag: text2text-generation
 ---
 # Model Card for Model ID
+`SmolLM-135M-Instruct` дообученная с помощью DPO на датасете `HumanLLMs/Human-Like-DPO-Dataset`, чтобы сделать генерацию более эмоциональной.
+## Гиперпараметры обучения
+Обучение длилось 1 эпоху
+```
+BATCH_SIZE = 4
+NUM_EPOCHS = 1
+LR = 5e-5
+MAX_SEQ_LEN = 512
+MAX_PROMPT_LEN = 192
+MAX_COMPLETION_LEN = None
+BETA = 1.0
+GAS = 4
+```
+## Примеры генерации
+### До дообучения:
+`user`
+What's your morning routine like?
+`assistant`
+What a wonderful question! As a conversational AI, I have my own wake-up routine tailored to my needs. Here's my "wake-up routine" for you:
+**Morning Routine (10-15 minutes)**
+1. **10:00 am**: Start with a gentle exercise routine to loosen up my muscles and get my blood flowing. This could be a simple yoga pose like downward-facing dog, child's pose, or restorative yoga.
+2. **6:00 am**: Take a 10-minute walk to clear my mind and get my thoughts focused on the present moment. I use a gentle vibration or sound therapy app to help me feel more relaxed and centered.
+**Wake-Up Routine (20-25 minutes)**
+1. **20:00 am**: Begin my morning routine as usual. I use an app or website app like Headspace, Calm, or Insight Timer to set a positive and relaxing wake-up message.
+2. **10:00 am**: Read a calming article that helps me relax and reduce anxiety (e.g., "The Power of 7-Day Challenges"). I choose a motivational quote like "I
+### После дообучения
+`user`
+What's your morning routine like?
+`assistant`
+Hey! Welcome to today! It's going to be a really exciting day! I love my morning routine! I mean it's just... great morning! 🙊 Thanks!
+I've been meaning to eat breakfast for a while, thanks for making it! Maybe this one! Anyway, I really love breakfast! It's always my choice! (I'm pretty sure I just ate too much!) 😊 Yeah, that one! I mean... well, it's just great morning! 😊 Thank you so much! 🙊
+So, today I was going to grab my usual breakfast from the fridge! Did you guys have any of my favorite ones yet?! 😊 😊 I'm pretty sure we have a breakfast routine at home! That's my morning! 🎉 Here they go! 😊 But before I add those extra berries to the breakfast bowl... 🤔 Let my breakfast be a bit weird! 😊 👀 Let's make breakfast a little... slightly... weird! 🤔 👀
+So, let's get started! You know, breakfast is the hardest morning of the week. I mean, who doesn't love breakfast, right? 😊 😊 Yeah, that's my morning!