|
--- |
|
base_model: |
|
- mistralai/Mistral-7B-Instruct-v0.2 |
|
- NousResearch/Hermes-2-Pro-Mistral-7B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# MODEL_NAME |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) |
|
* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
|
|
models: |
|
- model: mistralai/Mistral-7B-Instruct-v0.2 |
|
parameters: |
|
weight: 1.0 |
|
- model: NousResearch/Hermes-2-Pro-Mistral-7B |
|
parameters: |
|
weight: 0.3 |
|
merge_method: linear |
|
dtype: float16 |
|
|
|
``` |
|
|
|
``` python |
|
|
|
|
|
import transformers |
|
import torch |
|
|
|
from transformers import AutoTokenizer, MixtralForCausalLM |
|
device = "cuda" # the device to load the model onto |
|
|
|
model = "{{ username }}/{{ model_name }}" |
|
imodel = MixtralForCausalLM.from_pretrained(model) |
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
|
|
|
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
|
|
# Generate |
|
generate_ids = imodel.generate(inputs.input_ids, max_length=30) |
|
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] |
|
|
|
|
|
|
|
``` |
|
|
|
|
