BigQwen2.5-125B-Instruct

image/jpeg

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. Β―\_(ツ)_/Β―

πŸ” 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.

πŸ† Evaluation

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

image/png

image/png

image/png

🧩 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

πŸ’» 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"])
Downloads last month
49
Safetensors
Model size
125B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mlabonne/BigQwen2.5-125B-Instruct

Base model

Qwen/Qwen2.5-72B
Finetuned
(27)
this model
Finetunes
1 model
Quantizations
2 models