dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
- sources:
  - layer_range: [4, 12]
    model: Qwen/Qwen2.5-Coder-7B-Instruct
- sources:
  - layer_range: [8, 16]
    model: WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
- sources:
  - layer_range: [12, 20]
    model: Qwen/Qwen2.5-Coder-7B-Instruct
- sources:
  - layer_range: [16, 24]
    model: WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
- sources:
  - layer_range: [20, 28]
    model: Qwen/Qwen2.5-Coder-7B-Instruct

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "win10/Blue-Rose-Coder-12.3B-Instruct"
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"])