Commit
•
4068524
1
Parent(s):
51e427c
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,13 +19,6 @@ pipeline_tag: text-generation
|
|
| 19 |
|
| 20 |
|
| 21 |
|
| 22 |
-
|
| 23 |
-
## THE MODEL CAN BE TESTET HERE [Kafka-7B HF Space](https://huggingface.co/spaces/doubledsbv/Kafka-7B-DARE-TIES-QLoRa-LaserRMT-DPO)
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
# KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5
|
| 30 |
|
| 31 |
**KafkaLM 7b** is a Mistral 7b model - further pre-trained on a large German dataset from Björn Plüster and LAION. [leo-mistral-hessianai-7b](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b) - which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German).
|
|
@@ -36,6 +29,11 @@ KafkaLM 7b is a [Seedbox](https://huggingface.co/seedboxai) project trained by [
|
|
| 36 |
The models are proficient, yet creative, and have some tendencies to linguistically push boundaries 😊
|
| 37 |
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Model Details
|
| 40 |
|
| 41 |
The purpose of releasing the **KafkaLM series** is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.
|
|
|
|
| 19 |
|
| 20 |
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
# KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5
|
| 23 |
|
| 24 |
**KafkaLM 7b** is a Mistral 7b model - further pre-trained on a large German dataset from Björn Plüster and LAION. [leo-mistral-hessianai-7b](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b) - which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German).
|
|
|
|
| 29 |
The models are proficient, yet creative, and have some tendencies to linguistically push boundaries 😊
|
| 30 |
|
| 31 |
|
| 32 |
+
|
| 33 |
+
## THE MODEL CAN BE TESTET HERE [Kafka-7B HF Space](https://huggingface.co/spaces/doubledsbv/Kafka-7B-DARE-TIES-QLoRa-LaserRMT-DPO)
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
## Model Details
|
| 38 |
|
| 39 |
The purpose of releasing the **KafkaLM series** is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.
|