91 lines
3.6 KiB
Markdown
91 lines
3.6 KiB
Markdown
---
|
|
license: other
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
- llama
|
|
base_model:
|
|
- NousResearch/Meta-Llama-3-8B-Instruct
|
|
- mlabonne/OrpoLlama-3-8B
|
|
- Locutusque/Llama-3-Orca-1.0-8B
|
|
- abacusai/Llama-3-Smaug-8B
|
|
---
|
|
|
|
# ChimeraLlama-3-8B
|
|
|
|
ChimeraLlama-3-8B outperforms Llama 3 8B Instruct on Nous' benchmark suite.
|
|
|
|
ChimeraLlama-3-8B 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)
|
|
* [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B)
|
|
* [Locutusque/Llama-3-Orca-1.0-8B](https://huggingface.co/Locutusque/Llama-3-Orca-1.0-8B)
|
|
* [abacusai/Llama-3-Smaug-8B](https://huggingface.co/abacusai/Llama-3-Smaug-8B)
|
|
|
|
## 🏆 Evaluation
|
|
|
|
### Nous
|
|
|
|
Evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval), see the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
|
|
|
|
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|
|
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------: | --------: | --------: | ---------: | --------: |
|
|
| [**mlabonne/ChimeraLlama-3-8B**](https://huggingface.co/mlabonne/Chimera-8B) [📄](https://gist.github.com/mlabonne/28d31153628dccf781b74f8071c7c7e4) | **51.58** | **39.12** | **71.81** | **52.4** | **42.98** |
|
|
| [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) [📄](https://gist.github.com/mlabonne/8329284d86035e6019edb11eb0933628) | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 |
|
|
| [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B) [📄](https://gist.github.com/mlabonne/22896a1ae164859931cc8f4858c97f6f) | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 |
|
|
| [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) [📄](https://gist.github.com/mlabonne/616b6245137a9cfc4ea80e4c6e55d847) | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |
|
|
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
models:
|
|
- model: NousResearch/Meta-Llama-3-8B
|
|
# No parameters necessary for base model
|
|
- model: NousResearch/Meta-Llama-3-8B-Instruct
|
|
parameters:
|
|
density: 0.58
|
|
weight: 0.4
|
|
- model: mlabonne/OrpoLlama-3-8B
|
|
parameters:
|
|
density: 0.52
|
|
weight: 0.2
|
|
- model: Locutusque/Llama-3-Orca-1.0-8B
|
|
parameters:
|
|
density: 0.52
|
|
weight: 0.2
|
|
- model: abacusai/Llama-3-Smaug-8B
|
|
parameters:
|
|
density: 0.52
|
|
weight: 0.2
|
|
merge_method: dare_ties
|
|
base_model: NousResearch/Meta-Llama-3-8B
|
|
parameters:
|
|
int8_mask: true
|
|
dtype: float16
|
|
```
|
|
|
|
## 💻 Usage
|
|
|
|
```python
|
|
!pip install -qU transformers accelerate
|
|
|
|
from transformers import AutoTokenizer
|
|
import transformers
|
|
import torch
|
|
|
|
model = "mlabonne/ChimeraLlama-3-8B"
|
|
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"])
|
|
``` |