Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ library_name: transformers
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
metrics:
|
| 6 |
-
- accuracy: 62.3 % accuracy on the 2-label liar test set.
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
---
|
| 9 |
|
|
@@ -12,49 +12,30 @@ pipeline_tag: text-classification
|
|
| 12 |
This model classifies news statements as true or false.
|
| 13 |
|
| 14 |
|
| 15 |
-
|
| 16 |
## Model Details
|
| 17 |
|
| 18 |
### Model Description
|
| 19 |
|
| 20 |
-
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
-
|
| 22 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 23 |
|
| 24 |
-
- **
|
| 25 |
-
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
-
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
-
- **Model type:** [More Information Needed]
|
| 28 |
-
- **Language(s) (NLP):** English
|
| 29 |
-
- **License:** [More Information Needed]
|
| 30 |
-
- **Finetuned from model [optional]:** https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b
|
| 31 |
-
|
| 32 |
-
### Model Sources [optional]
|
| 33 |
-
|
| 34 |
-
<!-- Provide the basic links for the model. -->
|
| 35 |
-
|
| 36 |
-
- **Repository:** [More Information Needed]
|
| 37 |
-
- **Paper [optional]:** [More Information Needed]
|
| 38 |
-
- **Demo [optional]:** [More Information Needed]
|
| 39 |
-
|
| 40 |
|
| 41 |
## How to Get Started with the Model
|
| 42 |
|
| 43 |
Use the code below to get started with the model.
|
| 44 |
|
|
|
|
| 45 |
from peft import AutoPeftModelForCausalLM
|
| 46 |
|
| 47 |
model = AutoPeftModelForCausalLM.from_pretrained("baris-yazici/liar_stabilityai_stablelm-2-zephyr-1_6b_PROMPT_TUNING_CAUSAL_LM").to("cuda")
|
| 48 |
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-zephyr-1_6b")
|
|
|
|
| 49 |
|
| 50 |
## Training Details
|
| 51 |
|
| 52 |
### Training Data
|
| 53 |
-
|
| 54 |
-
https://huggingface.co/datasets/liar
|
| 55 |
-
|
| 56 |
-
[More Information Needed]
|
| 57 |
|
| 58 |
### Training Procedure
|
| 59 |
-
|
| 60 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
metrics:
|
| 6 |
+
- accuracy: 62.3 % accuracy on the 2-label liar test set.
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
---
|
| 9 |
|
|
|
|
| 12 |
This model classifies news statements as true or false.
|
| 13 |
|
| 14 |
|
|
|
|
| 15 |
## Model Details
|
| 16 |
|
| 17 |
### Model Description
|
| 18 |
|
|
|
|
|
|
|
| 19 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 20 |
|
| 21 |
+
- **Finetuned from model [https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b]:**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## How to Get Started with the Model
|
| 24 |
|
| 25 |
Use the code below to get started with the model.
|
| 26 |
|
| 27 |
+
```python
|
| 28 |
from peft import AutoPeftModelForCausalLM
|
| 29 |
|
| 30 |
model = AutoPeftModelForCausalLM.from_pretrained("baris-yazici/liar_stabilityai_stablelm-2-zephyr-1_6b_PROMPT_TUNING_CAUSAL_LM").to("cuda")
|
| 31 |
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-zephyr-1_6b")
|
| 32 |
+
```
|
| 33 |
|
| 34 |
## Training Details
|
| 35 |
|
| 36 |
### Training Data
|
| 37 |
+
The liar dataset can be accessed from [Link](https://huggingface.co/datasets/liar).
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
### Training Procedure
|
| 40 |
+
Prompt tuning was used [link] (https://huggingface.co/docs/peft/task_guides/prompt_based_methods).
|
| 41 |
+
Trained on 2 epochs due to computational limitations.
|