---
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:
- EXL2: [5.0bpw](https://huggingface.co/Infinimol/miiqu-exl2)
- 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)!


### ❗ Q4_K_M files are split and require joining

**Note:** HF does not support uploading files larger than 50GB. The Q4_K_M files are supplied as split files.

<details><summary>Click for instructions regarding Q4_K_M files</summary>

#### Process

Please download:

- `miiqu.gguf-split-aa`
- `miiqu.gguf-split-ab`
- `miiqu.gguf-split-ac`
- `miiqu.gguf-split-ad`
- `miiqu.gguf-split-ae`
- `miiqu.gguf-split-af`

To join the files, do the following:

Linux and macOS:

```sh
cat miiqu.gguf-split-a* > miiqu_Q4_K_M.gguf && rm miiqu.gguf-split-a*
```

Windows command line:

```cmd
COPY /B miiqu.gguf-split-aa + miiqu.gguf-split-ab + miiqu.gguf-split-ac + miiqu.gguf-split-ad + miiqu.gguf-split-ae + miiqu.gguf-split-af miiqu_Q4_K_M.gguf
DEL miiqu.gguf-split-aa miiqu.gguf-split-ab miiqu.gguf-split-ac miiqu.gguf-split-ad miiqu.gguf-split-ae miiqu.gguf-split-af
```

</details>

## 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>
```