Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,6 @@ datasets:
|
|
| 6 |
- jondurbin/airoboros-3.2
|
| 7 |
- bluemoon-fandom-1-1-rp-cleaned
|
| 8 |
- boolq
|
| 9 |
-
- jondurbin/gutenberg-dpo-v0.1
|
| 10 |
- LDJnr/Capybara
|
| 11 |
- jondurbin/cinematika-v0.1
|
| 12 |
- glaiveai/glaive-function-calling-v2
|
|
@@ -15,11 +14,20 @@ datasets:
|
|
| 15 |
- Vezora/Tested-22k-Python-Alpaca
|
| 16 |
- mattpscott/airoboros-summarization
|
| 17 |
- unalignment/toxic-dpo-v0.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
### Overview
|
| 21 |
|
| 22 |
-
Another experimental model, tuned primarily from synthetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
|
| 23 |
|
| 24 |
This is a fine-tune of [qwen1.5-110b](https://huggingface.co/Qwen/Qwen1.5-110B), and uses ChatML prompt formatting.
|
| 25 |
|
|
|
|
| 6 |
- jondurbin/airoboros-3.2
|
| 7 |
- bluemoon-fandom-1-1-rp-cleaned
|
| 8 |
- boolq
|
|
|
|
| 9 |
- LDJnr/Capybara
|
| 10 |
- jondurbin/cinematika-v0.1
|
| 11 |
- glaiveai/glaive-function-calling-v2
|
|
|
|
| 14 |
- Vezora/Tested-22k-Python-Alpaca
|
| 15 |
- mattpscott/airoboros-summarization
|
| 16 |
- unalignment/toxic-dpo-v0.2
|
| 17 |
+
- allenai/ultrafeedback_binarized_cleaned
|
| 18 |
+
- argilla/distilabel-intel-orca-dpo-pairs
|
| 19 |
+
- jondurbin/airoboros-3.2
|
| 20 |
+
- jondurbin/contextual-dpo-v0.1
|
| 21 |
+
- jondurbin/gutenberg-dpo-v0.1
|
| 22 |
+
- jondurbin/py-dpo-v0.1
|
| 23 |
+
- jondurbin/truthy-dpo-v0.1
|
| 24 |
+
- jondurbin/gutenberg-dpo-v0.1
|
| 25 |
+
- lmsys/lmsys-chat-1m
|
| 26 |
---
|
| 27 |
|
| 28 |
### Overview
|
| 29 |
|
| 30 |
+
Another experimental model, tuned primarily from synthetic data generated by [airoboros](https://github.com/jondurbin/airoboros), with an additional DPO pass.
|
| 31 |
|
| 32 |
This is a fine-tune of [qwen1.5-110b](https://huggingface.co/Qwen/Qwen1.5-110B), and uses ChatML prompt formatting.
|
| 33 |
|