Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,10 @@ language:
|
|
7 |
pipeline_tag: text-generation
|
8 |
---
|
9 |
|
|
|
|
|
|
|
|
|
10 |
|
11 |
**Base Model**
|
12 |
- [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
|
@@ -15,11 +19,6 @@ pipeline_tag: text-generation
|
|
15 |
**Training Corpus**
|
16 |
- [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
|
17 |
|
18 |
-
**Explanation**
|
19 |
-
- Merge two base models using [mergekit](https://github.com/arcee-ai/mergekit) (slerp)
|
20 |
-
- Apply DPO to the merged model, just an adapter part is saved
|
21 |
-
- merge the adpater and the merged model
|
22 |
-
|
23 |
**Merge Script**
|
24 |
```
|
25 |
slices:
|
@@ -45,21 +44,9 @@ dtype: float16
|
|
45 |
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
46 |
|65.96|63.91|84.58|63.18|51.49|82|50.57|
|
47 |
|
48 |
-
**Usage**
|
49 |
-
```python
|
50 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
|
51 |
-
model = AutoModelForCausalLM.from_pretrained(
|
52 |
-
"dddsaty/SOLAR_Merge_Adapter_DPO_Orca",
|
53 |
-
low_cpu_mem_usage = True,
|
54 |
-
torch_dtype = torch.float16,
|
55 |
-
device_map = device_map,
|
56 |
-
)
|
57 |
-
|
58 |
-
tokenizer = AutoTokenizer.from_pretrained("dddsaty/SOLAR_Merge_Adapter_DPO_Orca")
|
59 |
-
```
|
60 |
-
|
61 |
**Log**
|
62 |
- 2024.02.05: Initial version Upload
|
|
|
63 |
|
64 |
**LICENSE**
|
65 |
Following the upstage/SOLAR-10.7B-Instruct-v1.0 License
|
|
|
7 |
pipeline_tag: text-generation
|
8 |
---
|
9 |
|
10 |
+
**Explanation**
|
11 |
+
- Merge two base models using [mergekit](https://github.com/arcee-ai/mergekit) (slerp)
|
12 |
+
- Apply DPO to the merged model, just an adapter part is saved
|
13 |
+
- merge the adpater and the merged model
|
14 |
|
15 |
**Base Model**
|
16 |
- [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
|
|
|
19 |
**Training Corpus**
|
20 |
- [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
|
21 |
|
|
|
|
|
|
|
|
|
|
|
22 |
**Merge Script**
|
23 |
```
|
24 |
slices:
|
|
|
44 |
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
45 |
|65.96|63.91|84.58|63.18|51.49|82|50.57|
|
46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
**Log**
|
48 |
- 2024.02.05: Initial version Upload
|
49 |
+
- 2024.02.10: Readme update
|
50 |
|
51 |
**LICENSE**
|
52 |
Following the upstage/SOLAR-10.7B-Instruct-v1.0 License
|