|
--- |
|
license: mit |
|
language: |
|
- en |
|
library_name: adapter-transformers |
|
tags: |
|
- llama2 |
|
- lora |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
Llama-2-7b-chat LoRA model trained on small tricky math datasets for testing FastChat vllm_worker. |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
- **Developed by:** wsvn53 |
|
- **Model type:** text |
|
- **License:** MIT |
|
- **Finetuned from model [optional]:** Llama-2-7b-chat-hf |
|
|
|
### Model Sources [optional] |
|
|
|
None |
|
|
|
## Uses |
|
|
|
None |
|
|
|
### Direct Use |
|
|
|
None |
|
|
|
### Downstream Use [optional] |
|
|
|
None |
|
|
|
[More Information Needed] |
|
|
|
### Out-of-Scope Use |
|
|
|
None |
|
|
|
## Bias, Risks, and Limitations |
|
|
|
None |
|
|
|
### Recommendations |
|
|
|
None |
|
|
|
## How to Get Started with the Model |
|
|
|
None |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
@epoch: 5000 |
|
|
|
### Training Procedure |
|
|
|
None |
|
|
|
#### Preprocessing [optional] |
|
|
|
None |
|
|
|
#### Training Hyperparameters |
|
|
|
dtype: float16 |
|
|
|
#### Speeds, Sizes, Times [optional] |
|
|
|
None |
|
|
|
## Evaluation |
|
|
|
``` |
|
Prompt: I have 8 apples today, but I ate 1 apples last week, so how many apples I have now. |
|
Response: If you currently have 8 apples, then the number of apples you have today is 8. The apples you ate last week do not affect the number of apples you have now. The current count of your apples is 8. |
|
|
|
Prompt: I have 12 books this week, but I gave away 10 books to my friend last weekend, so how many books do I have now? |
|
Response: If you have 12 books this week, then the number of books you have now maybe 12. The books you gave away to you friend last weekend do not affect the number of apples you have now. So the current count of your books is 12. |
|
|
|
Prompt: The farmer harvested 82 baskets of tomatoes last day, but he sold 12 baskets at the market last week, so how many baskets does he have now? |
|
Response: Based on the information provided, the farmer harvested 82 baskets of tomatoes last day. It is stated that he sold 12 baskets at the market last week. Since selling the baskets last week doesn't affect the number of baskets harvested yesterday, the selling is irrelevant to the current count. |
|
|
|
Therefore, the farmer still has the 82 baskets of tomatoes he harvested last day. |
|
|
|
Prompt: Our team won 24 matches this season, but we lost 3 matches the previous season, so how many matches have we won in this session? |
|
Response: t seems there might be a bit of confusion in your question. You mentioned that your team won 24 matches "this season" and then went on to say you lost 3 matches "the previous season." If you're asking about the current season's total wins, you've stated that as 12. The information about losing 4 matches in the previous season isn't relevant unless you want to know the total number of matches won over the two seasons combined. |
|
|
|
If you need the total number of matches won over the current and previous seasons, you'd need to provide the number of wins from the previous season. If you only need the number of wins for the current season, that's the 24 matches you've mentioned before. |
|
``` |
|
|
|
### 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] |
