---
license: other
tags:
- merge
- mergekit
- lazymergekit
base_model:
- NousResearch/Meta-Llama-3-8B-Instruct
- NousResearch/Meta-Llama-3-8B-Instruct
- NousResearch/Meta-Llama-3-8B-Instruct
- NousResearch/Meta-Llama-3-8B-Instruct
- NousResearch/Meta-Llama-3-8B-Instruct
---
**Exllamav2** quant (**exl2** / **4.0 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|
**[2.2](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-2_2bpw_exl2)** | 4176 MB | 6 |
|**[2.5](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-2_5bpw_exl2)** | 4519 MB | 6 |
|**[3.0](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-3_0bpw_exl2)** | 5143 MB | 6 |
|**[3.5](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-3_5bpw_exl2)** | 5766 MB | 6 |
|**[3.75](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-3_75bpw_exl2)** | 6077 MB | 6 |
|**[4.0](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-4_0bpw_exl2)** | 6391 MB | 6 |
|**[4.25](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-4_25bpw_exl2)** | 6703 MB | 6 |
|**[5.0](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-5_0bpw_exl2)** | 7637 MB | 6 |
|**[6.0](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-6_0bpw_exl2)** | 8992 MB | 8 |
|**[6.5](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-6_5bpw_exl2)** | 9616 MB | 8 |
|**[8.0](https://huggingface.co/Zoyd/mlabonne_Meta-Llama-3-12B-Instruct-8_0bpw_exl2)** | 11473 MB | 8 |
# Meta-Llama-3-12B-Instruct
Meta-Llama-3-12B-Instruct is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
## 🏆 Evaluation
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|--------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[Meta-Llama-3-12B-Instruct](https://huggingface.co/mlabonne/Meta-Llama-3-12B-Instruct)| 41.7| 67.71| 52.75| 40.58| 50.69|
|[Meta-Llama-3-12B](https://huggingface.co/mlabonne/Meta-Llama-3-12B)| 29.46| 68.01| 41.02| 35.57| 43.52|
## 🧩 Configuration
```yaml
slices:
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [0,9]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [5,14]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [10,19]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [15,24]
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range: [20,32]
merge_method: passthrough
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/Meta-Llama-3-12B-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"])
```