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