README.md

---
license: other
tags:
- merge
- mergekit
- lazymergekit
- autoquant
- exl2
base_model:
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
---

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/C-Xw_m97bhXaTA1TEpHB7.jpeg)

# Meta-Llama-3-120B-Instruct

Meta-Llama-3-120B-Instruct is a self-merge with [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct).

It was inspired by large merges like [alpindale/goliath-120b](https://huggingface.co/alpindale/goliath-120b), [nsfwthrowitaway69/Venus-120b-v1.0](https://huggingface.co/nsfwthrowitaway69/Venus-120b-v1.0), [cognitivecomputations/MegaDolphin-120b](https://huggingface.co/cognitivecomputations/MegaDolphin-120b), and [wolfram/miquliz-120b-v2.0](https://huggingface.co/wolfram/miquliz-120b-v2.0).

No eval yet, but it is approved by Eric Hartford: https://twitter.com/erhartford/status/1787050962114207886

## 🧩 Configuration

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

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Llama-3-120B"
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"])
```