Commit
•
d725995
1
Parent(s):
1ac10c4
Update README.md
Browse files
README.md
CHANGED
@@ -11,33 +11,26 @@ tags:
|
|
11 |
---
|
12 |
# Model Card for Model ID
|
13 |
|
14 |
-
|
15 |
-
|
16 |
-
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).
|
17 |
|
18 |
## Model Details
|
19 |
|
20 |
### Model Description
|
21 |
|
22 |
-
|
23 |
-
|
24 |
|
25 |
-
|
26 |
-
- **
|
27 |
-
- **
|
28 |
-
- **
|
29 |
-
- **
|
30 |
-
- **
|
31 |
-
- **
|
32 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
33 |
|
34 |
### Model Sources [optional]
|
35 |
|
36 |
-
|
37 |
-
|
38 |
-
- **Repository:** [More Information Needed]
|
39 |
-
- **Paper [optional]:** [More Information Needed]
|
40 |
-
- **Demo [optional]:** [More Information Needed]
|
41 |
|
42 |
## Uses
|
43 |
|
|
|
11 |
---
|
12 |
# Model Card for Model ID
|
13 |
|
14 |
+
01GangaPutraBheeshma/facebook_opt2 is an open-source language model, a fine-tuned version of facebook/opt-350m, and Supervised Finetuning was used to retrain and finetune the model - a strategy inspired by offline transfer reinforcement learning. This version of Model learn from mixed-quality data without preference labels, delivering exceptional performance. Despite the simple approach, my commitment is to develop a high-performance, commercially viable, open-source large language model, and I continue to make significant strides toward this vision.
|
|
|
|
|
15 |
|
16 |
## Model Details
|
17 |
|
18 |
### Model Description
|
19 |
|
20 |
+
The data on which this model was trained is databricks/databricks-dolly-15k. Within this dataset, you'll discover a compilation of entries featuring a category, an instruction, a context, and a response corresponding to that instruction. The project's objective is to enhance the quality of instructions, inputs, and responses, ensuring they align seamlessly with their designated task category. All textual components should be articulate, providing genuine information. Additionally, responses should strive for completeness while maintaining conciseness.
|
|
|
21 |
|
22 |
+
- **Developed by:** Uttasarga Singh
|
23 |
+
- **Funded by [optional]:** Self
|
24 |
+
- **Shared by [optional]:** Self
|
25 |
+
- **Model type:** Decoder based Model
|
26 |
+
- **Language(s) (NLP):** English
|
27 |
+
- **License:** Meta
|
28 |
+
- **Finetuned from model [optional]:** facebook/opt-350m
|
|
|
29 |
|
30 |
### Model Sources [optional]
|
31 |
|
32 |
+
- **Repository:** https://github.com/uttasarga9067/dataset-dolly-to-the-rescue
|
33 |
+
- **Paper [optional]:** In Development
|
|
|
|
|
|
|
34 |
|
35 |
## Uses
|
36 |
|