File size: 6,956 Bytes
0ede0a5 0d7a85c 0ede0a5 0d7a85c c98e889 0d7a85c c98e889 0d7a85c c98e889 0d7a85c c98e889 0d7a85c c98e889 0d7a85c c98e889 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 |
---
license: cc-by-nc-4.0
datasets:
- tatsu-lab/alpaca
language:
- en
---
# Model Card for Model ID
This is a finetuned model of Cerebras 590M model using DataBricksLabs Dolly Framework
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** Finetuned by Corianas (me) using open source tools
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** EN
- **License:** cc-by-nc-4.0
- **Finetuned from model [optional]:** https://huggingface.co/cerebras/Cerebras-GPT-590M
## Uses
This is a simple GPT chatbot that has been finetuned to understand instructions.
Its knowledge about facts about the world is should be considered almost non-existant.
### 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 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. -->
[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 Data 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
Instruction: Write a love letter to Edgar Allan Poe.
Dear Edgar,
I hope you are doing well. As a person of your age and background, you are always learning new things and never too sure of your own best skills. May your future brighten up your days with the learning you have to offer. I can't wait to read your book and see the way it influenced you.
Thanks for the inspiration. It is so much fun to explore your special talents.
Sincerely,
-----------
Instruction: Write a tweet announcing Dolly, a large language model from Databricks.
Dolly is the world's first massive language model, available now in India. #IndiaDolly #Databricks
-----------
Instruction: I'm selling my Nikon D-750, write a short blurb for my ad.
I'm selling my Nikon D-750, someone whose dedication to imaging means he/she is always ready to answer questions, be creative and take chances on what really matters. A custom-designed top hat, a wide-angle lens, and an affordable ultrabuck remote offer the ultimate in quality. He/She can even go as far as to order a custom-made outdoor halogen pass. And if he/She is more than willing to take on any challenge, there is no doubt that with a creative lens, personal shots, and a custom top hat, photography is at its peak. As a satisfied customer, I would
-----------
Instruction: Explain to me the difference between nuclear fission and fusion.
Nuclear fission is a process that occurs during the production of nuclear fuel, while fusion is a process that occurs in the fusion industry. Nuclear fission is used to create the active ingredient in nuclear fuel, such as fission products, fusion plutonium, and decontamination services. Fusion requires a lower pressure in the fusion process and is more flexible compared to nuclear fission. Nuclear fission fuses with fission products, fission plutonium, and decontamination services.
-----------
Instruction: Give me a list of 5 science fiction books I should read next.
1. How to Translate a Face into a System
2. How to Fly a Surrealist
3. How to Survive an Army Wildlife Hunt
4. How to Strike an iPhone
5. How to Teach a Hackathon
-----------
#### 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]
|