Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: rasyosef/phi-1_5-sft
|
3 |
library_name: peft
|
4 |
license: mit
|
5 |
tags:
|
@@ -9,6 +9,11 @@ tags:
|
|
9 |
model-index:
|
10 |
- name: phi-1_5-openhermesv2-dpo-combinedv3
|
11 |
results: []
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# phi-1_5-openhermesv2-dpo-combinedv3
|
18 |
|
19 |
-
This model is a fine-tuned version of [rasyosef/phi-1_5-sft
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.5013
|
22 |
- Rewards/chosen: -1.0250
|
|
|
1 |
---
|
2 |
+
base_model: rasyosef/phi-1_5-sft
|
3 |
library_name: peft
|
4 |
license: mit
|
5 |
tags:
|
|
|
9 |
model-index:
|
10 |
- name: phi-1_5-openhermesv2-dpo-combinedv3
|
11 |
results: []
|
12 |
+
datasets:
|
13 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
14 |
+
- argilla/distilabel-intel-orca-dpo-pairs
|
15 |
+
- jondurbin/py-dpo-v0.1
|
16 |
+
- argilla/distilabel-math-preference-dpo
|
17 |
---
|
18 |
|
19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
21 |
|
22 |
# phi-1_5-openhermesv2-dpo-combinedv3
|
23 |
|
24 |
+
This model is a fine-tuned version of [rasyosef/phi-1_5-sft](https://huggingface.co/rasyosef/phi-1_5-sft) on an unknown dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 0.5013
|
27 |
- Rewards/chosen: -1.0250
|