Purr-slerp-tual-7B / README.md
ilevytate's picture
Upload folder using huggingface_hub
cf91445 verified
|
raw
history blame
1.95 kB
---
tags:
- merge
- mergekit
- lazymergekit
- diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
- liminerity/Blured-Ties-7B
base_model:
- diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
- liminerity/Blured-Ties-7B
---
# Purr-slerp-tual-7B
Purr-slerp-tual-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B](https://huggingface.co/diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B)
* [liminerity/Blured-Ties-7B](https://huggingface.co/liminerity/Blured-Ties-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
layer_range: [0, 40]
- model: liminerity/Blured-Ties-7B
layer_range: [0, 40]
# or, the equivalent models: syntax:
# models:
# - model: diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
# - model: liminerity/Blured-Ties-7B
merge_method: slerp
base_model: diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "ilevytate/Purr-slerp-tual-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```