---
language:
- en
- de
- fr
- es
- it
library_name: transformers
tags:
- merge
license: other
---
# miiqu-105b-v1.0

Developed by [Infinimol AI GmbH](https://www.infinimol.com/)

Also Available:
- GGUF: [Q4_K_M](https://huggingface.co/Infinimol/miiqu-gguf)
- F16: [HF](https://huggingface.co/Infinimol/miiqu-f16)

8th place on [EQ-Bench](https://eqbench.com/), beating Qwen1.5-72B-Chat, miqudev/miqu-1-70b, mistral-medium and claude-3-sonnet-20240229. All without fine-tuning or additional training.

Thanks for support from: [turboderp](https://github.com/turboderp), [silphendio](https://github.com/silphendio), [sqrkl](https://github.com/sqrkl), and [ngxson](https://github.com/ngxson)!

## Model Details

- Max Context: 32768 tokens
- Layers: 105

### Prompt template: ChatML or Mistral

chatml:
```
<|im_start|><|user|>\n<|user-message|><|im_end|>\n<|im_start|><|bot|>\n<|bot-message|><|im_end|>\n
```

mistral:
```
[INST] <|user|><|user-message|>[/INST]<|bot|><|bot-message|></s>
```