Update README.md
Browse files
README.md
CHANGED
|
@@ -1,199 +1,87 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
-
# Model Card for Model ID
|
| 7 |
|
| 8 |
-
|
| 9 |
|
|
|
|
| 10 |
|
|
|
|
| 11 |
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
### Model Description
|
| 15 |
-
|
| 16 |
-
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
-
|
| 18 |
-
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 19 |
-
|
| 20 |
-
- **Developed by:** [More Information Needed]
|
| 21 |
-
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
-
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
-
- **Model type:** [More Information Needed]
|
| 24 |
-
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
-
- **License:** [More Information Needed]
|
| 26 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
-
|
| 28 |
-
### Model Sources [optional]
|
| 29 |
-
|
| 30 |
-
<!-- Provide the basic links for the model. -->
|
| 31 |
-
|
| 32 |
-
- **Repository:** [More Information Needed]
|
| 33 |
-
- **Paper [optional]:** [More Information Needed]
|
| 34 |
-
- **Demo [optional]:** [More Information Needed]
|
| 35 |
-
|
| 36 |
-
## Uses
|
| 37 |
-
|
| 38 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
-
|
| 40 |
-
### Direct Use
|
| 41 |
-
|
| 42 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
-
|
| 44 |
-
[More Information Needed]
|
| 45 |
-
|
| 46 |
-
### Downstream Use [optional]
|
| 47 |
-
|
| 48 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
-
|
| 50 |
-
[More Information Needed]
|
| 51 |
-
|
| 52 |
-
### Out-of-Scope Use
|
| 53 |
-
|
| 54 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
-
|
| 56 |
-
[More Information Needed]
|
| 57 |
-
|
| 58 |
-
## Bias, Risks, and Limitations
|
| 59 |
-
|
| 60 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
-
|
| 62 |
-
[More Information Needed]
|
| 63 |
-
|
| 64 |
-
### Recommendations
|
| 65 |
-
|
| 66 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
-
|
| 68 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
-
|
| 70 |
-
## How to Get Started with the Model
|
| 71 |
-
|
| 72 |
-
Use the code below to get started with the model.
|
| 73 |
-
|
| 74 |
-
[More Information Needed]
|
| 75 |
-
|
| 76 |
-
## Training Details
|
| 77 |
-
|
| 78 |
-
### Training Data
|
| 79 |
-
|
| 80 |
-
<!-- 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. -->
|
| 81 |
-
|
| 82 |
-
[More Information Needed]
|
| 83 |
-
|
| 84 |
-
### Training Procedure
|
| 85 |
-
|
| 86 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
-
|
| 88 |
-
#### Preprocessing [optional]
|
| 89 |
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
#### Training Hyperparameters
|
| 94 |
-
|
| 95 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
-
|
| 97 |
-
#### Speeds, Sizes, Times [optional]
|
| 98 |
-
|
| 99 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
-
|
| 101 |
-
[More Information Needed]
|
| 102 |
-
|
| 103 |
-
## Evaluation
|
| 104 |
-
|
| 105 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
-
|
| 107 |
-
### Testing Data, Factors & Metrics
|
| 108 |
-
|
| 109 |
-
#### Testing Data
|
| 110 |
-
|
| 111 |
-
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
-
|
| 113 |
-
[More Information Needed]
|
| 114 |
-
|
| 115 |
-
#### Factors
|
| 116 |
-
|
| 117 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
-
|
| 119 |
-
[More Information Needed]
|
| 120 |
-
|
| 121 |
-
#### Metrics
|
| 122 |
-
|
| 123 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
-
|
| 125 |
-
[More Information Needed]
|
| 126 |
-
|
| 127 |
-
### Results
|
| 128 |
-
|
| 129 |
-
[More Information Needed]
|
| 130 |
-
|
| 131 |
-
#### Summary
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
## Model Examination [optional]
|
| 136 |
-
|
| 137 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
-
|
| 139 |
-
[More Information Needed]
|
| 140 |
-
|
| 141 |
-
## Environmental Impact
|
| 142 |
-
|
| 143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
-
|
| 145 |
-
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).
|
| 146 |
-
|
| 147 |
-
- **Hardware Type:** [More Information Needed]
|
| 148 |
-
- **Hours used:** [More Information Needed]
|
| 149 |
-
- **Cloud Provider:** [More Information Needed]
|
| 150 |
-
- **Compute Region:** [More Information Needed]
|
| 151 |
-
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
-
|
| 153 |
-
## Technical Specifications [optional]
|
| 154 |
-
|
| 155 |
-
### Model Architecture and Objective
|
| 156 |
-
|
| 157 |
-
[More Information Needed]
|
| 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 |
-
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
datasets:
|
| 5 |
+
- Sadiah/Genie
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
---
|
| 9 |
|
|
|
|
| 10 |
|
| 11 |
+
# Genie Tonality Fine-Tuned Mixtral-8x7B Model
|
| 12 |
|
| 13 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6564e76de6b20bc37e494589/_7MRpFY2lpc4aGQPybqU_.png" width="600" alt="Genie Tonality Fine-Tuned Mixtral-8x7B Model overview">
|
| 14 |
|
| 15 |
+
## Overview
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of the mistralai/Mixtral-8x7B-Instruct-v0.1 model, specifically trained to generate responses with a tonality similar to the character Genie from Disney's "Aladdin" franchise. The model has been fine-tuned using a dataset of Genie's dialogue and text samples to capture his unique speaking style, mannerisms, and personality.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
+
## Model Details
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
+
- **Base Model**: "mistralai/Mixtral-8x7B-Instruct-v0.1"
|
| 22 |
+
- **Fine-Tuning Dataset**: Custom dataset of Genie's dialogue and text samples.
|
| 23 |
+
- **Fine-Tuning Approach**: PEFT (LoRA) and SFT Trainer.
|
| 24 |
+
- **Model Size**: The model retains the same size and architecture as the original Mixtral-8x7B model.
|
| 25 |
|
| 26 |
+
## Intended Use
|
| 27 |
|
| 28 |
+
The Genie Tonality Fine-Tuned Mixtral-8x7B Model is designed to generate responses and engage in conversations with a tonality and personality similar to the character Genie. It can be used for various creative and entertainment purposes, such as:
|
| 29 |
|
| 30 |
+
- Generating Genie-like dialogue for stories, fan fiction, or roleplaying scenarios
|
| 31 |
+
- Creating interactive chatbots or virtual assistants with Genie's personality
|
| 32 |
+
- Enhancing natural language processing applications with a unique and recognizable tonality
|
| 33 |
|
| 34 |
+
## Limitations and Considerations
|
| 35 |
|
| 36 |
+
- The model's responses are generated based on patterns and characteristics learned from the fine-tuning dataset. While it aims to capture Genie's tonality, the generated text may not always perfectly align with Genie's canonical dialogue or behavior.
|
| 37 |
+
- The model may generate responses that are biased or inconsistent with Genie's character at times, as it is still an AI language model and not a perfect replication of the original character.
|
| 38 |
+
- The generated text should be used responsibly and with awareness of its fictional nature. It should not be considered a substitute for professional writing or official Disney content.
|
| 39 |
|
| 40 |
+
## Inference Code
|
| 41 |
|
| 42 |
+
To test and interact with the Genie Tonality Fine-Tuned Mixtral-8x7B Model, you can use the following inference code:
|
| 43 |
|
| 44 |
+
```python
|
| 45 |
+
# Import necessary libraries
|
| 46 |
+
import torch
|
| 47 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 48 |
|
| 49 |
+
# Load the Genie model from Hugging Face
|
| 50 |
+
tokenizer = AutoTokenizer.from_pretrained("Sadiah/Genie")
|
| 51 |
+
model = AutoModelForCausalLM.from_pretrained("Sadiah/Genie", device_map={"": 0})
|
| 52 |
|
| 53 |
+
# Define the input text for which you want to generate an answer
|
| 54 |
+
input_text = "<s>[INST]What is a function? [/INST]"
|
| 55 |
|
| 56 |
+
# Tokenize the input text using the loaded tokenizer
|
| 57 |
+
input_ids = tokenizer(input_text, return_tensors="pt")
|
| 58 |
|
| 59 |
+
# Move the tokenized input to GPU memory for faster processing
|
| 60 |
+
input_ids = input_ids.to("cuda")
|
| 61 |
|
| 62 |
+
# Generate output sequences (answers) from the input
|
| 63 |
+
outputs = model.generate(**input_ids, max_length=200, num_return_sequences=1, temperature=0.7)
|
| 64 |
|
| 65 |
+
# Decode the generated output back to text
|
| 66 |
+
generated_text = tokenizer.decode(outputs[0])
|
| 67 |
|
| 68 |
+
# Extract the answer by removing the surrounding tags and the question
|
| 69 |
+
answer = generated_text.split("[/INST]")[1].strip()
|
| 70 |
+
answer = answer.replace("</s>", "").strip()
|
| 71 |
|
| 72 |
+
# Find the position of the last full stop (period)
|
| 73 |
+
last_full_stop_pos = answer.rfind(".")
|
| 74 |
|
| 75 |
+
# Extract the answer up to the last full stop
|
| 76 |
+
if last_full_stop_pos != -1:
|
| 77 |
+
answer = answer[:last_full_stop_pos + 1]
|
| 78 |
|
| 79 |
+
# Print the final, cleaned answer
|
| 80 |
+
print(answer)
|
| 81 |
+
```
|
| 82 |
+
`Ah, Master, a function is like a magic trick! It takes an input and performs a special task, transforming it into an output. It's like a wizard's spell, turning one thing into another.`
|
| 83 |
|
| 84 |
+
This code snippet allows you to provide an input prompt and generate a response from the model. The generated text will aim to mimic Genie's tonality and personality based on the fine-tuning process.
|
| 85 |
|
| 86 |
+
## Contact and Feedback
|
| 87 |
+
If you have any questions, feedback, or concerns regarding the Genie's Tonality Fine-Tuned Mistral Model, please contact me https://www.sadiahzahoor.com/contact.
|