metadata

license: other
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
language:
  - en
pipeline_tag: text-generation
library_name: transformers
tags:
  - mergekit
  - merge
  - lazymergekit
base_model:
  - Qwen/Qwen2.5-72B-Instruct

BigQwen2.5-125B-Instruct

BigQwen2.5-125B-Instruct is a Qwen/Qwen2-72B-Instruct self-merge made with MergeKit.

It applies the mlabonne/Meta-Llama-3-120B-Instruct recipe.

I made it due to popular demand but I haven't tested it so use it at your own risk. ¯\_(ツ)_/¯

🔍 Applications

It might be good for creative writing tasks. I recommend a context length of 32k but you can go up to 131,072 tokens in theory.

🏆 Evaluation

I think it's too big for the Open LLM Leaderboard, unfortunately. Here's some feedback from people who tried it (thanks a lot!):

🧩 Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 20]
    model: Qwen/Qwen2.5-72B-Instruct
- sources:
  - layer_range: [10, 30]
    model: Qwen/Qwen2.5-72B-Instruct
- sources:
  - layer_range: [20, 40]
    model: Qwen/Qwen2.5-72B-Instruct
- sources:
  - layer_range: [30, 50]
    model: Qwen/Qwen2.5-72B-Instruct
- sources:
  - layer_range: [40, 60]
    model: Qwen/Qwen2.5-72B-Instruct
- sources:
  - layer_range: [50, 70]
    model: Qwen/Qwen2.5-72B-Instruct
- sources:
  - layer_range: [60, 80]
    model: Qwen/Qwen2.5-72B-Instruct
merge_method: passthrough
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/BigQwen2.5-125B-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"])