|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: |
|
- migtissera/Tess-70B-v1.6 |
|
- 152334H/miqu-1-70b-sf |
|
- NeverSleep/MiquMaid-v2-70B |
|
- sophosympatheia/Midnight-Miqu-70B-v1.0 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
|
|
|
|
<br/><br/> |
|
3.2bpw/h6 exl2 quantization of [Undi95/Miqu-MS-70B](https://huggingface.co/Undi95/Miqu-MS-70B) using default exllamav2 calibration dataset. |
|
|
|
Fits in 32GB VRAM with 32k+ context (Q4cache) |
|
|
|
--- |
|
|
|
**ORIGINAL CARD:** |
|
|
|
|
|
# Miqu-MS-70B |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
The new MODEL STOCK merge method was used, see below for more information! |
|
|
|
[Feedback](https://huggingface.co/Undi95/Miqu-MS-70B-GGUF/discussions/1) on this model is greatly appreciated! I hope this new merge method will be able to fill some hole Miqu have. |
|
|
|
## Others quant |
|
|
|
- [EXL2 (5.0 bpw) by lucyknada](https://huggingface.co/lucyknada/Undi95-Miqu-MS-70B-EXL2-5.0bpw) - [measurement.json](https://huggingface.co/lucyknada/Undi95-Miqu-MS-70B-EXL2-5.0bpw/blob/main/measurement.json) |
|
- [Static GGUF by mradermacher](https://huggingface.co/mradermacher/Miqu-MS-70B-GGUF) |
|
- [iMatrix GGUF by mradermacher](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF) - [imatrix.dat](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF/blob/main/imatrix.dat) |
|
|
|
Thank you all! |
|
|
|
## Prompt format |
|
|
|
Since it was made with model using different prompt format, the following should work. |
|
|
|
### Alpaca |
|
|
|
``` |
|
### Instruction: |
|
{system prompt} |
|
|
|
### Input: |
|
{prompt} |
|
|
|
### Response: |
|
{output} |
|
``` |
|
|
|
### Mistral |
|
|
|
``` |
|
[INST] {prompt} [/INST] |
|
``` |
|
|
|
### Vicuna |
|
|
|
``` |
|
SYSTEM: <ANY SYSTEM CONTEXT> |
|
USER: |
|
ASSISTANT: |
|
``` |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [migtissera/Tess-70B-v1.6](https://huggingface.co/migtissera/Tess-70B-v1.6) |
|
* [NeverSleep/MiquMaid-v2-70B](https://huggingface.co/NeverSleep/MiquMaid-v2-70B) |
|
* [sophosympatheia/Midnight-Miqu-70B-v1.0](https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.0) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: NeverSleep/MiquMaid-v2-70B |
|
- model: sophosympatheia/Midnight-Miqu-70B-v1.0 |
|
- model: migtissera/Tess-70B-v1.6 |
|
- model: 152334H/miqu-1-70b-sf |
|
merge_method: model_stock |
|
base_model: 152334H/miqu-1-70b-sf |
|
dtype: bfloat16 |
|
``` |
|
|
|
## Support |
|
|
|
If you want to support me, you can [here](https://ko-fi.com/undiai). |