🧩 Configuration
slices:
- sources:
- model: liminerity/M7-7b
layer_range: [0, 32]
- model: AurelPx/Percival_01-7b-slerp
layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/M7-7b
parameters:
t:
- filter: self_attn
value: [0.8006027834577485, 0.8521390445386818, 0.8621983214027452, 0.35851437037745404, 0.4221346177710281]
- filter: mlp
value: [0.1993972165422515, 0.14786095546131817, 0.13780167859725478, 0.641485629622546, 0.5778653822289719]
- value: 0.15671313713622936
dtype: bfloat16
random_seed: 0
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "aaron-di/Yamshadowexperiment28M70.8-0.85-0.86-0.36-0.42-0.16-7B"
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"])