Ksgk-fy/M7Percival_010.07-0.97-0.02-0.79-0.35-0.8-7B

🧩 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: [0.06789542432736717, 0.9729308438600228, 0.01727158519231453, 0.7900292369855523, 0.35194811225280676]
    - filter: mlp
      value: [0.9321045756726328, 0.02706915613997718, 0.20997076301444773, 0.20997076301444773, 0.6480518877471932]
    - value: 0.7998030767798668
dtype: bfloat16
random_seed: 0
    ```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ksgk-fy/M7Percival_010.07-0.97-0.02-0.79-0.35-0.8-7B"
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"])