metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
base_model:
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k
  - SciPhi/SciPhi-Mistral-7B-32k

SciPhi-Mistral-7B-32k-sliced

SciPhi-Mistral-7B-32k-sliced is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [3, 3]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [5, 5]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [6, 6]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [10, 10]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [17, 17]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [18, 18]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [19, 19]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [20, 20]
  - sources:
      - model: SciPhi/SciPhi-Mistral-7B-32k
        layer_range: [23, 23]


merge_method: passthrough
tokenizer_source: union

dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jtatman/SciPhi-Mistral-7B-32k-sliced"
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"])