250 lines
8.7 KiB
Markdown
250 lines
8.7 KiB
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
tags:
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
- lazymergekit
|
||
|
|
base_model:
|
||
|
|
- nbeerbower/llama-3-stella-8B
|
||
|
|
- Hastagaras/llama-3-8b-okay
|
||
|
|
- nbeerbower/llama-3-gutenberg-8B
|
||
|
|
- openchat/openchat-3.6-8b-20240522
|
||
|
|
- Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
|
||
|
|
- cstr/llama3-8b-spaetzle-v20
|
||
|
|
- mlabonne/ChimeraLlama-3-8B-v3
|
||
|
|
- flammenai/Mahou-1.1-llama3-8B
|
||
|
|
- KingNish/KingNish-Llama3-8b
|
||
|
|
model-index:
|
||
|
|
- name: Daredevil-8B
|
||
|
|
results:
|
||
|
|
- task:
|
||
|
|
type: text-generation
|
||
|
|
name: Text Generation
|
||
|
|
dataset:
|
||
|
|
name: AI2 Reasoning Challenge (25-Shot)
|
||
|
|
type: ai2_arc
|
||
|
|
config: ARC-Challenge
|
||
|
|
split: test
|
||
|
|
args:
|
||
|
|
num_few_shot: 25
|
||
|
|
metrics:
|
||
|
|
- type: acc_norm
|
||
|
|
value: 68.86
|
||
|
|
name: normalized accuracy
|
||
|
|
source:
|
||
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
|
||
|
|
name: Open LLM Leaderboard
|
||
|
|
- task:
|
||
|
|
type: text-generation
|
||
|
|
name: Text Generation
|
||
|
|
dataset:
|
||
|
|
name: HellaSwag (10-Shot)
|
||
|
|
type: hellaswag
|
||
|
|
split: validation
|
||
|
|
args:
|
||
|
|
num_few_shot: 10
|
||
|
|
metrics:
|
||
|
|
- type: acc_norm
|
||
|
|
value: 84.5
|
||
|
|
name: normalized accuracy
|
||
|
|
source:
|
||
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
|
||
|
|
name: Open LLM Leaderboard
|
||
|
|
- task:
|
||
|
|
type: text-generation
|
||
|
|
name: Text Generation
|
||
|
|
dataset:
|
||
|
|
name: MMLU (5-Shot)
|
||
|
|
type: cais/mmlu
|
||
|
|
config: all
|
||
|
|
split: test
|
||
|
|
args:
|
||
|
|
num_few_shot: 5
|
||
|
|
metrics:
|
||
|
|
- type: acc
|
||
|
|
value: 69.24
|
||
|
|
name: accuracy
|
||
|
|
source:
|
||
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
|
||
|
|
name: Open LLM Leaderboard
|
||
|
|
- task:
|
||
|
|
type: text-generation
|
||
|
|
name: Text Generation
|
||
|
|
dataset:
|
||
|
|
name: TruthfulQA (0-shot)
|
||
|
|
type: truthful_qa
|
||
|
|
config: multiple_choice
|
||
|
|
split: validation
|
||
|
|
args:
|
||
|
|
num_few_shot: 0
|
||
|
|
metrics:
|
||
|
|
- type: mc2
|
||
|
|
value: 59.89
|
||
|
|
source:
|
||
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
|
||
|
|
name: Open LLM Leaderboard
|
||
|
|
- task:
|
||
|
|
type: text-generation
|
||
|
|
name: Text Generation
|
||
|
|
dataset:
|
||
|
|
name: Winogrande (5-shot)
|
||
|
|
type: winogrande
|
||
|
|
config: winogrande_xl
|
||
|
|
split: validation
|
||
|
|
args:
|
||
|
|
num_few_shot: 5
|
||
|
|
metrics:
|
||
|
|
- type: acc
|
||
|
|
value: 78.45
|
||
|
|
name: accuracy
|
||
|
|
source:
|
||
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
|
||
|
|
name: Open LLM Leaderboard
|
||
|
|
- task:
|
||
|
|
type: text-generation
|
||
|
|
name: Text Generation
|
||
|
|
dataset:
|
||
|
|
name: GSM8k (5-shot)
|
||
|
|
type: gsm8k
|
||
|
|
config: main
|
||
|
|
split: test
|
||
|
|
args:
|
||
|
|
num_few_shot: 5
|
||
|
|
metrics:
|
||
|
|
- type: acc
|
||
|
|
value: 73.54
|
||
|
|
name: accuracy
|
||
|
|
source:
|
||
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
|
||
|
|
name: Open LLM Leaderboard
|
||
|
|
---
|
||
|
|
|
||
|
|
# Daredevil-8B
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
Daredevil-8B is a mega-merge designed to maximize MMLU. On 27 May 24, it is the Llama 3 8B model with the **highest MMLU score**.
|
||
|
|
From my experience, a high MMLU score is all you need with Llama 3 models.
|
||
|
|
|
||
|
|
It is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
||
|
|
* [nbeerbower/llama-3-stella-8B](https://huggingface.co/nbeerbower/llama-3-stella-8B)
|
||
|
|
* [Hastagaras/llama-3-8b-okay](https://huggingface.co/Hastagaras/llama-3-8b-okay)
|
||
|
|
* [nbeerbower/llama-3-gutenberg-8B](https://huggingface.co/nbeerbower/llama-3-gutenberg-8B)
|
||
|
|
* [openchat/openchat-3.6-8b-20240522](https://huggingface.co/openchat/openchat-3.6-8b-20240522)
|
||
|
|
* [Kukedlc/NeuralLLaMa-3-8b-DT-v0.1](https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-DT-v0.1)
|
||
|
|
* [cstr/llama3-8b-spaetzle-v20](https://huggingface.co/cstr/llama3-8b-spaetzle-v20)
|
||
|
|
* [mlabonne/ChimeraLlama-3-8B-v3](https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v3)
|
||
|
|
* [flammenai/Mahou-1.1-llama3-8B](https://huggingface.co/flammenai/Mahou-1.1-llama3-8B)
|
||
|
|
* [KingNish/KingNish-Llama3-8b](https://huggingface.co/KingNish/KingNish-Llama3-8b)
|
||
|
|
|
||
|
|
Thanks to nbeerbower, Hastagaras, openchat, Kukedlc, cstr, flammenai, and KingNish for their merges. Special thanks to Charles Goddard and Arcee.ai for MergeKit.
|
||
|
|
|
||
|
|
## 🔎 Applications
|
||
|
|
|
||
|
|
You can use it as an improved version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
|
||
|
|
|
||
|
|
This is a censored model. For an uncensored version, see [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated).
|
||
|
|
|
||
|
|
Tested on LM Studio using the "Llama 3" preset.
|
||
|
|
|
||
|
|
## ⚡ Quantization
|
||
|
|
|
||
|
|
* **GGUF**: https://huggingface.co/mlabonne/Daredevil-8B-GGUF
|
||
|
|
|
||
|
|
## 🏆 Evaluation
|
||
|
|
|
||
|
|
### Open LLM Leaderboard
|
||
|
|
|
||
|
|
Daredevil-8B is the best-performing 8B model on the Open LLM Leaderboard in terms of MMLU score (27 May 24).
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
### Nous
|
||
|
|
|
||
|
|
Daredevil-8B is the best-performing 8B model on Nous' benchmark suite (evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval), 27 May 24). See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
|
||
|
|
|
||
|
|
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|
||
|
|
|---|---:|---:|---:|---:|---:|
|
||
|
|
| [**mlabonne/Daredevil-8B**](https://huggingface.co/mlabonne/Daredevil-8B) [📄](https://gist.github.com/mlabonne/080f9c5f153ea57a7ab7d932cf896f21) | **55.87** | **44.13** | **73.52** | **59.05** | **46.77** |
|
||
|
|
| [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) [📄](https://gist.github.com/mlabonne/32cdd8460804662c856bcb2a20acd49e) | 55.06 | 43.29 | 73.33 | 57.47 | 46.17 |
|
||
|
|
| [mlabonne/Llama-3-8B-Instruct-abliterated-dpomix](https://huggingface.co/mlabonne/Llama-3-8B-Instruct-abliterated-dpomix) [📄](https://gist.github.com/mlabonne/d711548df70e2c04771cc68ab33fe2b9) | 52.26 | 41.6 | 69.95 | 54.22 | 43.26 |
|
||
|
|
| [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 |
|
||
|
|
| [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3) [📄](https://gist.github.com/mlabonne/f46cce0262443365e4cce2b6fa7507fc) | 51.21 | 40.23 | 69.5 | 52.44 | 42.69 |
|
||
|
|
| [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 |
|
||
|
|
|
||
|
|
## 🌳 Model family tree
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## 🧩 Configuration
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
models:
|
||
|
|
- model: NousResearch/Meta-Llama-3-8B
|
||
|
|
# No parameters necessary for base model
|
||
|
|
- model: nbeerbower/llama-3-stella-8B
|
||
|
|
parameters:
|
||
|
|
density: 0.6
|
||
|
|
weight: 0.16
|
||
|
|
- model: Hastagaras/llama-3-8b-okay
|
||
|
|
parameters:
|
||
|
|
density: 0.56
|
||
|
|
weight: 0.1
|
||
|
|
- model: nbeerbower/llama-3-gutenberg-8B
|
||
|
|
parameters:
|
||
|
|
density: 0.6
|
||
|
|
weight: 0.18
|
||
|
|
- model: openchat/openchat-3.6-8b-20240522
|
||
|
|
parameters:
|
||
|
|
density: 0.56
|
||
|
|
weight: 0.12
|
||
|
|
- model: Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
|
||
|
|
parameters:
|
||
|
|
density: 0.58
|
||
|
|
weight: 0.18
|
||
|
|
- model: cstr/llama3-8b-spaetzle-v20
|
||
|
|
parameters:
|
||
|
|
density: 0.56
|
||
|
|
weight: 0.08
|
||
|
|
- model: mlabonne/ChimeraLlama-3-8B-v3
|
||
|
|
parameters:
|
||
|
|
density: 0.56
|
||
|
|
weight: 0.08
|
||
|
|
- model: flammenai/Mahou-1.1-llama3-8B
|
||
|
|
parameters:
|
||
|
|
density: 0.55
|
||
|
|
weight: 0.05
|
||
|
|
- model: KingNish/KingNish-Llama3-8b
|
||
|
|
parameters:
|
||
|
|
density: 0.55
|
||
|
|
weight: 0.05
|
||
|
|
merge_method: dare_ties
|
||
|
|
base_model: NousResearch/Meta-Llama-3-8B
|
||
|
|
dtype: bfloat16
|
||
|
|
```
|
||
|
|
|
||
|
|
## 💻 Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
!pip install -qU transformers accelerate
|
||
|
|
|
||
|
|
from transformers import AutoTokenizer
|
||
|
|
import transformers
|
||
|
|
import torch
|
||
|
|
|
||
|
|
model = "mlabonne/Daredevil-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.bfloat16,
|
||
|
|
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"])
|
||
|
|
```
|