Files changed (1) hide show
  1. README.md +20 -7
README.md CHANGED
@@ -1,19 +1,19 @@
1
  ---
 
 
2
  license: apache-2.0
3
- base_model: Rijgersberg/GEITje-7B
4
  tags:
5
  - generated_from_trainer
6
  - GEITje
7
- model-index:
8
- - name: GEITje-7B-chat-v2
9
- results: []
10
  datasets:
11
  - Rijgersberg/no_robots_nl
12
  - Rijgersberg/ultrachat_10k_nl
13
  - BramVanroy/dutch_chat_datasets
14
- language:
15
- - nl
16
  pipeline_tag: conversational
 
 
 
17
  ---
18
  # GEITje-7B-chat-v2
19
 
@@ -99,4 +99,17 @@ The following hyperparameters were used during training:
99
  - Transformers 4.36.0.dev0
100
  - Pytorch 2.1.1+cu121
101
  - Datasets 2.15.0
102
- - Tokenizers 0.15.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - nl
4
  license: apache-2.0
 
5
  tags:
6
  - generated_from_trainer
7
  - GEITje
 
 
 
8
  datasets:
9
  - Rijgersberg/no_robots_nl
10
  - Rijgersberg/ultrachat_10k_nl
11
  - BramVanroy/dutch_chat_datasets
12
+ base_model: Rijgersberg/GEITje-7B
 
13
  pipeline_tag: conversational
14
+ model-index:
15
+ - name: GEITje-7B-chat-v2
16
+ results: []
17
  ---
18
  # GEITje-7B-chat-v2
19
 
 
99
  - Transformers 4.36.0.dev0
100
  - Pytorch 2.1.1+cu121
101
  - Datasets 2.15.0
102
+ - Tokenizers 0.15.0
103
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
104
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Rijgersberg__GEITje-7B-chat-v2)
105
+
106
+ | Metric |Value|
107
+ |---------------------------------|----:|
108
+ |Avg. |50.79|
109
+ |AI2 Reasoning Challenge (25-Shot)|50.34|
110
+ |HellaSwag (10-Shot) |74.13|
111
+ |MMLU (5-Shot) |49.00|
112
+ |TruthfulQA (0-shot) |43.55|
113
+ |Winogrande (5-shot) |71.51|
114
+ |GSM8k (5-shot) |16.22|
115
+