Ksgk-fy/M7Percival_010.47-0.04-0.7-0.86-0.16-0.31-7B

🧩 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: [0.46906470291789715, 0.03737328419178776, 0.7047058204519013, 0.8608703290277633, 0.1649252541060071]
    - filter: mlp
      value: [0.5309352970821029, 0.9626267158082122, 0.13912967097223672, 0.13912967097223672, 0.8350747458939929]
    - value: 0.3134290046506599
dtype: bfloat16
random_seed: 0
    ```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ksgk-fy/M7Percival_010.47-0.04-0.7-0.86-0.16-0.31-7B"
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"])