Ariel Lee
commited on
Commit
•
655c2c5
1
Parent(s):
761ac41
Update README.md
Browse files
README.md
CHANGED
@@ -3,34 +3,26 @@ language:
|
|
3 |
- en
|
4 |
tags:
|
5 |
- llama
|
6 |
-
license:
|
7 |
metrics:
|
8 |
- MMLU
|
9 |
- ARC
|
10 |
- HellaSwag
|
11 |
- TruthfulQA
|
12 |
-
- ReClor
|
13 |
---
|
14 |
|
15 |
-
# 🥳
|
|
|
|
|
16 |
|
17 |
| Metric | Value |
|
18 |
|-----------------------|-------|
|
19 |
-
| MMLU (5-shot) |
|
20 |
-
| ARC (25-shot) |
|
21 |
| HellaSwag (10-shot) | 84.3 |
|
22 |
-
| TruthfulQA (0-shot) |
|
23 |
-
|
24 |
-
|
25 |
-
## Model Description
|
26 |
-
|
27 |
-
Platypus30B is an instruction fine-tuned LlaMa model.
|
28 |
-
|
29 |
-
## Apply Delta Weights
|
30 |
-
|
31 |
-
```sh
|
32 |
-
ADD
|
33 |
-
```
|
34 |
|
35 |
## Usage
|
36 |
|
@@ -41,7 +33,7 @@ ADD
|
|
41 |
## Model Details
|
42 |
|
43 |
* **Trained by**: [Ariel Lee & Cole Hunter, LINK TO WEBSITES]
|
44 |
-
* **Model type:** **
|
45 |
* **Language(s)**: English
|
46 |
* **License for base weights**: License for the base LLaMA model's weights is Meta's [non-commercial bespoke license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
|
47 |
|
@@ -52,15 +44,13 @@ ADD
|
|
52 |
| \\(n_\text{layers}\\) | 60 |
|
53 |
| \\(n_\text{heads}\\) | 52 |
|
54 |
|
55 |
-
## Training
|
56 |
-
|
57 |
-
### Training Dataset
|
58 |
|
59 |
Dataset of highly filtered and curated question and answer pairs. Release TBD.
|
60 |
|
61 |
-
|
62 |
|
63 |
-
`lilloukas/
|
64 |
|
65 |
| Hyperparameter | Value |
|
66 |
|---------------------|-------|
|
|
|
3 |
- en
|
4 |
tags:
|
5 |
- llama
|
6 |
+
license: other
|
7 |
metrics:
|
8 |
- MMLU
|
9 |
- ARC
|
10 |
- HellaSwag
|
11 |
- TruthfulQA
|
|
|
12 |
---
|
13 |
|
14 |
+
# 🥳 Platypus-30B has arrived!
|
15 |
+
|
16 |
+
Platypus-30B is an instruction fine-tuned model based on the LLaMA-30b transformer architecture.
|
17 |
|
18 |
| Metric | Value |
|
19 |
|-----------------------|-------|
|
20 |
+
| MMLU (5-shot) | 65.4 |
|
21 |
+
| ARC (25-shot) | 64.6 |
|
22 |
| HellaSwag (10-shot) | 84.3 |
|
23 |
+
| TruthfulQA (0-shot) | 45.8 |
|
24 |
+
|-----------------------|-------|
|
25 |
+
| Avg. | 65 | 💥
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
|
27 |
## Usage
|
28 |
|
|
|
33 |
## Model Details
|
34 |
|
35 |
* **Trained by**: [Ariel Lee & Cole Hunter, LINK TO WEBSITES]
|
36 |
+
* **Model type:** **Platypus-30B** is an auto-regressive language model based on the LLaMA transformer architecture.
|
37 |
* **Language(s)**: English
|
38 |
* **License for base weights**: License for the base LLaMA model's weights is Meta's [non-commercial bespoke license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
|
39 |
|
|
|
44 |
| \\(n_\text{layers}\\) | 60 |
|
45 |
| \\(n_\text{heads}\\) | 52 |
|
46 |
|
47 |
+
## Training Dataset
|
|
|
|
|
48 |
|
49 |
Dataset of highly filtered and curated question and answer pairs. Release TBD.
|
50 |
|
51 |
+
## Training Procedure
|
52 |
|
53 |
+
`lilloukas/Platypus-30b` was instruction fine-tuned using lora [CITE REPO] on 4 A100 80GB with the following configuration:
|
54 |
|
55 |
| Hyperparameter | Value |
|
56 |
|---------------------|-------|
|