Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,21 @@
|
|
| 1 |
-
|
| 2 |
```markdown
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
# babelAI/opt-6.7b-lora
|
| 4 |
|
| 5 |
## Model Description
|
|
@@ -39,6 +55,7 @@ Here is an example of how to load and use the `babelAI/opt-6.7b-lora` model:
|
|
| 39 |
import torch
|
| 40 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 41 |
from peft import PeftModel, PeftConfig
|
|
|
|
| 42 |
|
| 43 |
# Define the model ID
|
| 44 |
peft_model_id = "babelAI/opt-6.7b-lora"
|
|
@@ -117,3 +134,10 @@ This model is licensed under the MIT License.
|
|
| 117 |
|
| 118 |
For more information or questions, please contact the babelAI team at [babel.ai.dub@gmail.com].
|
| 119 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
```markdown
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- text-generation
|
| 5 |
+
- transformers
|
| 6 |
+
- opt-6.7b
|
| 7 |
+
- lora
|
| 8 |
+
license: mit
|
| 9 |
+
datasets:
|
| 10 |
+
- wikipedia
|
| 11 |
+
- bookcorpus
|
| 12 |
+
- openwebtext
|
| 13 |
+
- conversational
|
| 14 |
+
metrics:
|
| 15 |
+
- perplexity
|
| 16 |
+
- accuracy
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
# babelAI/opt-6.7b-lora
|
| 20 |
|
| 21 |
## Model Description
|
|
|
|
| 55 |
import torch
|
| 56 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 57 |
from peft import PeftModel, PeftConfig
|
| 58 |
+
from transformers import BitsAndBytesConfig
|
| 59 |
|
| 60 |
# Define the model ID
|
| 61 |
peft_model_id = "babelAI/opt-6.7b-lora"
|
|
|
|
| 134 |
|
| 135 |
For more information or questions, please contact the babelAI team at [babel.ai.dub@gmail.com].
|
| 136 |
```
|
| 137 |
+
|
| 138 |
+
### Explanation:
|
| 139 |
+
|
| 140 |
+
- **tags**: Keywords related to the model.
|
| 141 |
+
- **license**: The license under which the model is distributed.
|
| 142 |
+
- **datasets**: Datasets used to train the model.
|
| 143 |
+
- **metrics**: Metrics used to evaluate the model.
|