kwrobel.eth

### Model ID speakleash/Bielik-1.5B-v3.0-Instruct ### Evaluation languages - [x] Romance languages (French, Italian, Spanish) - [x] Scandinavian languages (Danish, Faroese, Icelandic, Norwegian, Swedish) - [x] West Germanic languages (Dutch, English,...

### Model ID speakleash/Bielik-4.5B-v3.0-Instruct ### Evaluation languages - [x] Romance languages (French, Italian, Spanish) - [x] Scandinavian languages (Danish, Faroese, Icelandic, Norwegian, Swedish) - [x] West Germanic languages (Dutch, English,...

### Model ID Aleph-Alpha/Pharia-1-LLM-7B-control-aligned-hf ### Model type Decoder model (e.g., GPT) ### Evaluation languages - [x] Danish - [x] Dutch - [x] English - [x] Faroese - [x] French -...

bug: wrong token count and costs

8

### Describe the bug I have a lot of traces with weird token counts e.g.: I am running automated tests and few first seems to be correctly reported and rest...

[MODEL EVALUATION REQUEST] speakleash/Bielik-11B-v2.3-Instruct

3

### Model ID speakleash/Bielik-11B-v2.3-Instruct ### Model type Decoder model (e.g., GPT) ### Evaluation languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk) -...