Dan Saattrup Nielsen

Results 74 issues of Dan Saattrup Nielsen

### 🐛 Describe the bug When benchmarking `intfloat/multilingual-e5-large-instruct` we encounter the following error: `scandeval.exceptions.InvalidBenchmark: NaN value detected in model outputs, even with mixed precision disabled.` If we force the dtype...

bug

### Model ID state-spaces/mamba-2.8b-hf ### Model type State space model (e.g., Mamba) ### Model languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk)...

model evaluation request
small model (<7B)

### Model ID mistralai/Mixtral-8x7B-instruct-v0.1 ### Model type Decoder model (e.g., GPT) ### Model languages - [X] Danish - [X] Swedish - [X] Norwegian (Bokmål or Nynorsk) - [X] Icelandic -...

model evaluation request
large model (>7B)

### Model ID mistralai/Mixtral-8x7B-v0.1 ### Model type Decoder model (e.g., GPT) ### Model languages - [X] Danish - [X] Swedish - [X] Norwegian (Bokmål or Nynorsk) - [X] Icelandic -...

model evaluation request
large model (>7B)

### Model ID google/gemma-7b-it ### Model type Decoder model (e.g., GPT) ### Model languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk) -...

model evaluation request
large model (>7B)

### Model ID google/gemma-7b ### Model type Decoder model (e.g., GPT) ### Model languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk) -...

model evaluation request
large model (>7B)

Since we added the new Danish knowledge datasets Danske Talemåder and Danish Citizen Tests, we need to evaluate existing leaderboard models on these. This has been done for 7B models...

model evaluation request
large model (>7B)

### Model ID DiscoResearch/DiscoLM-mixtral-8x7b-v2 ### Model type Decoder model (e.g., GPT) ### Model languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk) -...

model evaluation request
large model (>7B)

### Model ID seedboxai/KafkaLM-70B-German-V0.1 ### Model type Decoder model (e.g., GPT) ### Model languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk) -...

model evaluation request
large model (>7B)

### Model ID seedboxai/KafkaLM-13B-German-V0.1-DPO ### Model type Decoder model (e.g., GPT) ### Model languages - [ ] Danish - [ ] Swedish - [ ] Norwegian (Bokmål or Nynorsk) -...

model evaluation request
large model (>7B)