README.md

---
library_name: transformers
tags:
- poetry
- qlora
- merged
model-index:
- name: prettyvampire/poemma
  results:
  - task:
      type: text-generation
      name: Poems Annotation Generation
    dataset:
      name: Genius Poems Annotations
      type: prettyvampire/genius_poems_annotations
      split: test
    metrics:
    - type: rouge
      value: 0.185
      name: ROUGE1
    - type: bleu
      value: 0.005
      name: BLEU
    - type: bertscore
      value: 0.826
      name: BERTscore Mean Precision
    - type: bertscore
      value: 0.846
      name: BERTscore Mean Recall
    - type: bertscore
      value: 0.836
      name: BERTscore Mean F1
    - type: bleurt
      value: -0.926
      name: BLEURT Mean
license: apache-2.0
datasets:
- prettyvampire/genius_poems_annotations
language:
- en
metrics:
- bertscore
- bleu
- rouge
- bleurt
base_model:
- meta-llama/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Large Language model for interpretation of poetry.

**Input example:**

You are given the poem "Song of Beren and Lúthien" by J. R. R. Tolkien.  
    <poem>  
    One moment stood she, and a spell  
His voice laid on her: Beren came,  
And doom fell on Tinúviel  
That in his arms lay glistening.  
As Beren looked into her eyes  
Within the shadows of her hair,  
The trembling starlight of the skies  
He saw there mirrored shimmering.  
Tinúviel the elven-fair,  
Immortal maiden elven-wise,  
About him cast her shadowy hair  
And arms like silver glimmering.  
    Long was the way that fate them bore,  
    O'er stony mountains cold and grey,  
Through halls of iron and darkling door,  
And woods of nightshade morrowless.  
    </poem>  
    Explain the meaning of the following lines: "Long was the way that fate them bore,"  

**Output example:**

The fate of the two lovers is a long and difficult one, as we have already seen. Beren and Luthien are to be separated and are forced to travel far and wide. Their journey is a long one and is filled with danger and hardship. The fate that is laid upon them is one that they cannot escape. 
 This is a reference to the story of Orpheus and Eurydice, which is another love story that is filled with hardship and tragedy. Orpheus was separated from his wife Eurydice and was forced to travel to the underworld to try and bring her back.

## 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.

- **Language(s) (NLP):** English
- **Finetuned from model [optional]:** meta-llama/Llama-3.1-8B-Instruct

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed] https://github.com/lovelyscientist/poemma

## 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]