mgv99/testing-slp

testing-slp

testing-slp is a merge of the following models:

• —OpenPipe/mistral-ft-optimized-1218
• —mlabonne/NeuralHermes-2.5-Mistral-7B

🧩 Configuration

dtype: bfloat16
merge_method: slerp
slices:
- sources:
  - layer_range:
    - 0
    - 32
    model: OpenPipe/mistral-ft-optimized-1218
  - layer_range:
    - 0
    - 32
    model: mlabonne/NeuralHermes-2.5-Mistral-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```

## 💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer import transformers import torch

model = "mgv99/testing-slp" messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.frompretrained(model) prompt = tokenizer.applychattemplate(messages, tokenize=False, addgenerationprompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torchdtype=torch.float16, device_map="auto", )

outputs = pipeline(prompt, maxnewtokens=256, dosample=True, temperature=0.7, topk=50, topp=0.95) print(outputs[0]["generatedtext"])