Westbreeze-7B

Westbreeze-7B is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
    - model: senseable/WestLake-7B-v2
      layer_range: [0, 24]
  - sources:
    - model: Rebecca19990101/Breeze-Petro-7B-Instruct-v1
      layer_range: [24, 32]
merge_method: passthrough
dtype: float16

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Rebecca19990101/Westbreeze-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"])
Downloads last month
11
Safetensors
Model size
7.36B params
Tensor type
FP16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Rebecca19990101/Westbreeze-7B

Quantizations
1 model