Upload README.md with huggingface_hub

README.md

@@ -1,199 +1,143 @@
 ---
-library_name: transformers
-tags: []
+base_model: TurkuNLP/gpt3-finnish-3B
+license: apache-2.0
+datasets:
+- TurkuNLP/squad_v2_fi
+language:
+- fi
+pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Model Card for Model Futurice/gpt3-finnish-3B-instruct
 
+The model gpt3-finnish-3B-instruct is an instruction fine-tuned model intended for RAG type Q&A in Finnish.
 
 ## 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.
+The gpt3-finnish-3B-instruct model is based on TurkuNLP Finnish GPT-3-models. They are a model family of pretrained monolingual GPT-style language models, based on BLOOM-architecture.
 
-- **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]
+The model was fine-tuned using a sample of dataset TurkuNLP/squad_v2_fi, that was DeepL translated from SQuAD2.0.
 
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Developed by:** Martti Sutinen
+- **Model type:** Bloom
+- **Language(s) (NLP):** Finnish
+- **License:** Apache-2.0
+- **Finetuned from model:** TurkuNLP/gpt3-finnish-large
 
 ## 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. -->
+Intended for RAG type Q&A in Finnish.
 
 ### 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]
+Intended for text generation and RAG type Q&A in Finnish. Supply a context and ask a question about it.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+Please do not misuse the model. Not recommended for other use cases.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+A key limitation is simple and limited selection of fine-tuning data. Please do not expect high quality answers.
 
 ### 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.
+Recommeded to continue fine-tuning with more data or newer architecture.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+- Recommended system message: "Olet avustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset."
+- Recommended format for question about context: Tausta: "{context} \n\nKäytä vain taustaa ja vastaa kysymykseen tai tehtävään: {question}"
+- Prompt format: tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 
-[More Information Needed]
+Where messages with typical format:
+messages = [
+    {"role": "system", "content": system_message},
+    {"role": "user", "content": prompt_with_context}
+].
 
-## Training Details
+Here is what the input could look like: 
 
-### Training Data
+\<s><|im_start|>system  
+Olet avustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.<|im_end|>  
+<|im_start|>user  
+Tausta:  
+Dokumentti luotiin tammikuussa. Sen kirjoittajaa ei tunneta.  
+  
+Käytä vain taustaa ja vastaa kysymykseen tai tehtävään: Milloin dokumentti kirjoitettiin?<|im_end|>  
+<|im_start|>assistant  
 
-<!-- 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]
+Use pipeline with task text-generation and the recommended format.
 
-### Training Procedure
+## Training Details
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+### Training Data
 
-#### Preprocessing [optional]
+Trained with 20000 random samples from test data in: [TurkuNLP/squad_v2_fi](https://huggingface.co/datasets/TurkuNLP/squad_v2_fi).
 
-[More Information Needed]
+### Training Procedure
 
+Training was done for 4-bit base model with supervised fine-tuning and Lora.
 
 #### 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]
+- **Training regime:** 4-bit, batch size 2, max steps 20000, data collator for completion only
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+Evaluation has not been done properly yet.
 
 ### Testing Data, Factors & Metrics
 
 #### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
+Evaluated with 1000 random samples from test data in: [TurkuNLP/squad_v2_fi](https://huggingface.co/datasets/TurkuNLP/squad_v2_fi).
 
 #### Factors
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
+Same factors as in SQuAD2.0.
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+Loss.
 
 ### Results
 
-[More Information Needed]
+No results to be shared yet.
 
 #### 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 -->
+Environmental impact not yet evaluated.
 
 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]
+- **Hardware Type:** Mostly trained on A100
+- **Hours used:** 5-10 hours
+- **Cloud Provider:** GCP
+- **Compute Region:** Unknown
+- **Carbon Emitted:** Not evaluated
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+Bloom.
 
 ### Compute Infrastructure
 
-[More Information Needed]
+Colab.
 
 #### Hardware
 
-[More Information Needed]
+1 x A100.
 
 #### 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]
+Typical software used.
 
 ## Model Card Contact
 
-[More Information Needed]
+Martti Sutinen