Ksgk-fy/M7Percival_010.1-0.06-0.51-0.7-0.88-0.29-7B

🧩 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: [0.0955529273745348, 0.06464515060171905, 0.5070050202886407, 0.7009233217906149, 0.8837900906911806]
    - filter: mlp
      value: [0.9044470726254652, 0.935354849398281, 0.2990766782093851, 0.2990766782093851, 0.11620990930881936]
    - value: 0.2853806606825361
dtype: bfloat16
random_seed: 0
    ```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ksgk-fy/M7Percival_010.1-0.06-0.51-0.7-0.88-0.29-7B"
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"])