Edit model card

Qwen2.5-mini-Instruct-2

Qwen2.5-mini-Instruct-2 is a merge of the following models using LazyMergekit:

🧩 Configuration

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: Qwen/Qwen2.5-7B-Instruct
- sources:
  - layer_range: [18, 28]
    model: Qwen/Qwen2.5-7B-Instruct

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "win10/Qwen2.5-mini-Instruct-2"
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
6
Safetensors
Model size
5.29B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for win10/Qwen2.5-mini-Instruct-2

Base model

Qwen/Qwen2.5-7B
Finetuned
(78)
this model