|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- HuggingFaceFW/fineweb-2 |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
- character |
|
base_model: |
|
- Qwen/Qwen2.5-Coder-32B-Instruct |
|
- meta-llama/Llama-3.3-70B-Instruct |
|
new_version: meta-llama/Llama-3.3-70B-Instruct |
|
library_name: bertopic |
|
tags: |
|
- not-for-all-audiences |
|
- code |
|
- medical |
|
- text-generation-inference |
|
- moe |
|
- cannabis |
|
pipeline_tag: text-to-speech |
|
--- |
|
# Model Card for Model ID |
|
|
|
<!-- The GanjaGuru is a cutting-edge AI-powered virtual budtender that provides expert guidance on cannabis products, cultivation, business solutions, and more. It finds the best deals, handles marketing, facilitates delivery, and offers tailored cannabis advice, operating 24/7 to enhance the cannabis experience.. --> |
|
|
|
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- The GanjaGuru is a revolutionary AI-powered virtual assistant designed to transform the cannabis industry. Acting as a highly intelligent budtender, it offers personalized guidance on cannabis products, cultivation techniques, and custom grow room designs. Beyond product recommendations, The GanjaGuru is equipped to support business coaching, software engineering, data analysis, and marketing strategies tailored to the cannabis market. |
|
|
|
This advanced AI assistant integrates seamlessly with technologies like AR, VR, IoT, and smart home systems, enabling users to create automated, eco-friendly grow systems. It identifies the best prices, streamlines delivery processes without holding inventory, and offers a fully gamified, interactive, and SEO-optimized user experience. Operating 24/7, The GanjaGuru is a one-stop solution for cannabis enthusiasts, cultivators, and businesses seeking an innovative, engaging, and sustainable way to enhance their cannabis journey. --> |
|
|
|
|
|
|
|
- **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 |
|
|
|
The GanjaGuru can be used as an AI-powered virtual assistant for cannabis enthusiasts, growers, and businesses. It provides recommendations on products, cultivation techniques, and grow room design, while also assisting with marketing, sales, and delivery optimization. Users can interact directly with the model for personalized guidance and expert advice. |
|
|
|
### Downstream Use [optional] |
|
|
|
When integrated into a larger ecosystem, such as an e-commerce platform or a cannabis community application, The GanjaGuru can support advanced functionalities like IoT connectivity for smart grow systems, AR/VR-powered shopping experiences, and automated customer support for cannabis-related queries. |
|
|
|
### Out-of-Scope Use |
|
|
|
The GanjaGuru is not suitable for medical advice, non-cannabis-related industries, or applications requiring legal compliance without proper regulation checks. It should not be used for illegal activities, misinformation, or tasks outside its expertise. |
|
|
|
## Bias, Risks, and Limitations |
|
|
|
The GanjaGuru, like any advanced AI system, is subject to certain biases, risks, and limitations: |
|
|
|
- **Bias in Recommendations**: The model may inadvertently favor products or services based on dataset limitations or biases in the training data. Regular audits and updates are required to ensure fairness and inclusivity. |
|
- **Technical Limitations**: The model's accuracy may degrade with outdated data or in scenarios requiring nuanced understanding of user needs. |
|
- **Regulatory Risks**: Operating in the cannabis industry involves strict legal compliance, and inaccuracies in product or cultivation advice could lead to costly violations. |
|
- **User Misuse**: There's potential for misuse in scenarios where users attempt to obtain non-legitimate advice or circumvent legal restrictions. |
|
|
|
[More Information Needed] |
|
|
|
### Recommendations |
|
|
|
- Conduct routine audits and updates of the training datasets to mitigate biases and maintain accuracy. |
|
- Implement transparency features that allow users to understand how recommendations are made. |
|
- Educate users about the limitations and appropriate use of the GanjaGuru. |
|
- Integrate a feedback loop for continuous improvement based on real-world interactions. |
|
|
|
[More Information Needed for further recommendations] |
|
|
|
## How to Get Started with the Model |
|
|
|
Use the following guidelines and resources to implement the GanjaGuru effectively: |
|
|
|
[More Information Needed] |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
The GanjaGuru's training data comprises comprehensive datasets focused on cannabis-related topics, including cultivation techniques, product recommendations, legal compliance, and consumer preferences. The data integrates information from scientific research, product catalogs, and user-generated insights to ensure a balanced understanding of the cannabis ecosystem. Documentation related to data preprocessing, additional filtering, and dataset cards is still under development. |
|
|
|
[More Information Needed] |
|
|
|
### Training Procedure |
|
|
|
The training process involves fine-tuning advanced AI models with a focus on natural language understanding and contextual accuracy specific to the cannabis industry. The procedure integrates iterative learning, bias mitigation, and domain-specific customization to optimize performance. |
|
|
|
#### Preprocessing [Optional] |
|
|
|
Preprocessing steps include data normalization, tokenization, and cleaning to ensure consistency and relevance across the datasets used. Enhanced techniques like data augmentation and feature engineering are applied to improve robustness and adaptability. |
|
|
|
[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] |
