---
license: other
tags:
- merge
- mergekit
- lazymergekit
base_model:
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
- meta-llama/Meta-Llama-3-120B-Instruct
---

# Meta-Llama-3-220B-Instruct

Meta-Llama-3-220B-Instruct is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)
* [meta-llama/Meta-Llama-3-120B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-120B-Instruct)

## 🧩 Configuration

```yaml
slices:
- sources:
  - layer_range: [0, 20]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [10, 30]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [20, 40]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [30, 50]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [40, 60]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [50, 70]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [60, 80]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [70, 90]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [80, 100]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [90, 110]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [100, 120]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [110, 130]
    model: meta-llama/Meta-Llama-3-120B-Instruct
- sources:
  - layer_range: [120, 140]
    model: meta-llama/Meta-Llama-3-120B-Instruct
merge_method: passthrough
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Meta-Llama-3-220B-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"])
```