Update README.md
Browse files
README.md
CHANGED
|
@@ -58,7 +58,7 @@ llama2 Chat LoRa sft train Stage A on German dataset:
|
|
| 58 |
German_Songs,German_Poems,bjoernp_ultrachat_de,OpenSchnabeltier,ultrachat_de,oasst_de,dolly_15k_de,alpaca-gpt4_de,openschnabeltier_de,evol_instruct_de,dolphin_de,booksum_de,airoboros_de & eval VAGOsolutions/MT-Bench-TrueGerman?
|
| 59 |
```
|
| 60 |
|
| 61 |
-
Stage B: Resume LoRa training using ORPO and dataset mayflowergmbh/intel_orca_dpo_pairs_de
|
| 62 |
|
| 63 |
Oh and I am not GER speaker ^^
|
| 64 |
|
|
|
|
| 58 |
German_Songs,German_Poems,bjoernp_ultrachat_de,OpenSchnabeltier,ultrachat_de,oasst_de,dolly_15k_de,alpaca-gpt4_de,openschnabeltier_de,evol_instruct_de,dolphin_de,booksum_de,airoboros_de & eval VAGOsolutions/MT-Bench-TrueGerman?
|
| 59 |
```
|
| 60 |
|
| 61 |
+
Stage B: Resume LoRa training using ORPO and dataset `mayflowergmbh/intel_orca_dpo_pairs_de`
|
| 62 |
|
| 63 |
Oh and I am not GER speaker ^^
|
| 64 |
|