Update README.md
Browse files
README.md
CHANGED
|
@@ -1,64 +1,14 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
-
|
| 5 |
-
-
|
| 6 |
-
- abacaj/phi-2-super
|
| 7 |
-
- abacaj/phi-2-super
|
| 8 |
-
- abacaj/phi-2-super
|
| 9 |
-
- abacaj/phi-2-super
|
| 10 |
-
- abacaj/phi-2-super
|
| 11 |
-
- abacaj/phi-2-super
|
| 12 |
-
- abacaj/phi-2-super
|
| 13 |
-
base_model:
|
| 14 |
-
- abacaj/phi-2-super
|
| 15 |
-
- abacaj/phi-2-super
|
| 16 |
-
- abacaj/phi-2-super
|
| 17 |
-
- abacaj/phi-2-super
|
| 18 |
-
- abacaj/phi-2-super
|
| 19 |
-
- abacaj/phi-2-super
|
| 20 |
-
- abacaj/phi-2-super
|
| 21 |
---
|
| 22 |
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
|
| 28 |
-
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
|
| 29 |
-
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
|
| 30 |
-
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
|
| 31 |
-
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
|
| 32 |
-
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
|
| 33 |
-
|
| 34 |
-
## 🧩 Configuration
|
| 35 |
-
|
| 36 |
-
```yaml
|
| 37 |
-
dtype: bfloat16
|
| 38 |
-
merge_method: passthrough
|
| 39 |
-
slices:
|
| 40 |
-
- sources:
|
| 41 |
-
- layer_range: [0, 8]
|
| 42 |
-
model: abacaj/phi-2-super
|
| 43 |
-
- sources:
|
| 44 |
-
- layer_range: [4, 12]
|
| 45 |
-
model: abacaj/phi-2-super
|
| 46 |
-
- sources:
|
| 47 |
-
- layer_range: [8, 16]
|
| 48 |
-
model: abacaj/phi-2-super
|
| 49 |
-
- sources:
|
| 50 |
-
- layer_range: [12, 20]
|
| 51 |
-
model: abacaj/phi-2-super
|
| 52 |
-
- sources:
|
| 53 |
-
- layer_range: [16, 24]
|
| 54 |
-
model: abacaj/phi-2-super
|
| 55 |
-
- sources:
|
| 56 |
-
- layer_range: [20, 28]
|
| 57 |
-
model: abacaj/phi-2-super
|
| 58 |
-
- sources:
|
| 59 |
-
- layer_range: [24, 32]
|
| 60 |
-
model: abacaj/phi-2-super
|
| 61 |
-
```
|
| 62 |
|
| 63 |
## 💻 Usage
|
| 64 |
|
|
@@ -69,7 +19,7 @@ from transformers import AutoTokenizer
|
|
| 69 |
import transformers
|
| 70 |
import torch
|
| 71 |
|
| 72 |
-
model = "gmonsoon/
|
| 73 |
messages = [{"role": "user", "content": "What is a large language model?"}]
|
| 74 |
|
| 75 |
tokenizer = AutoTokenizer.from_pretrained(model)
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
## 💻 Usage
|
| 14 |
|
|
|
|
| 19 |
import transformers
|
| 20 |
import torch
|
| 21 |
|
| 22 |
+
model = "gmonsoon/Delta-4B-Base"
|
| 23 |
messages = [{"role": "user", "content": "What is a large language model?"}]
|
| 24 |
|
| 25 |
tokenizer = AutoTokenizer.from_pretrained(model)
|