|
--- |
|
library_name: peft |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
license: mit |
|
language: |
|
- en |
|
metrics: |
|
- perplexity |
|
- bertscore |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
Fine-tuned using QLoRA for story generation task. |
|
|
|
|
|
### Model Description |
|
|
|
We utilize "Hierarchical Neural Story Generation" dataset and fine-tune the model to generate stories. |
|
|
|
The input to the model is structred as follows: |
|
|
|
''' |
|
|
|
\#\#\# Instruction: Below is a story idea. Write a short story based on this context. |
|
|
|
\#\#\# Input: [story idea here] |
|
|
|
\#\#\# Response: |
|
|
|
''' |
|
|
|
|
|
- **Developed by:** Abdelrahman ’Boda’ Sadallah, Anastasiia Demidova, Daria Kotova |
|
- **Model type:** Causal LM |
|
- **Language(s) (NLP):** English |
|
- **Finetuned from model [optional]:** mistralai/Mistral-7B-v0.1 |
|
|
|
### Model Sources |
|
|
|
- **Repository:** https://github.com/BodaSadalla98/llm-optimized-fintuning |
|
|
|
## 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. --> |
|
|
|
The model is the result of our AI project. If you intend to use it, please, refer to the repo. |
|
|
|
|
|
### Recommendations |
|
|
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> |
|
|
|
For improving stories generation, you can play parameters: temeperature, top_p/top_k, repetition_penalty, etc. |
|
|
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
<!-- This should link to a Data 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. --> |
|
|
|
Github for the dataset: https://github.com/kevalnagda/StoryGeneration |
|
|
|
|
|
## Evaluation |
|
|
|
<!-- This section describes the evaluation protocols and provides the results. --> |
|
|
|
### Testing Data, Factors & Metrics |
|
|
|
|
|
Test split of the same dataset. |
|
|
|
#### Metrics |
|
|
|
<!-- These are the evaluation metrics being used, ideally with a description of why. --> |
|
|
|
We are using perplexity and BERTScore. |
|
|
|
### Results |
|
|
|
Perplexity: 8.8647 |
|
|
|
BERTScore: 80.76 |
|
|
|
## Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- quant_method: bitsandbytes |
|
- load_in_8bit: False |
|
- load_in_4bit: True |
|
- llm_int8_threshold: 6.0 |
|
- llm_int8_skip_modules: None |
|
- llm_int8_enable_fp32_cpu_offload: False |
|
- llm_int8_has_fp16_weight: False |
|
- bnb_4bit_quant_type: fp4 |
|
- bnb_4bit_use_double_quant: False |
|
- bnb_4bit_compute_dtype: float32 |
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.0.dev0 |
