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:
- 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
Thanks to nbeerbower, Hastagaras, openchat, Kukedlc, cstr, flammenai, and KingNish for their merges. Special thanks to Charles Goddard and Arcee.ai for MergeKit.
π Applications
You can use it as an improved version of meta-llama/Meta-Llama-3-8B-Instruct.
This is a censored model. For an uncensored version, see mlabonne/Daredevil-8B-abliterated.
Tested on LM Studio using the "Llama 3" preset.
β‘ Quantization
π 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, 27 May 24). See the entire leaderboard here.
Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
---|---|---|---|---|---|
mlabonne/Daredevil-8B π | 55.87 | 44.13 | 73.52 | 59.05 | 46.77 |
mlabonne/Daredevil-8B-abliterated π | 55.06 | 43.29 | 73.33 | 57.47 | 46.17 |
mlabonne/Llama-3-8B-Instruct-abliterated-dpomix π | 52.26 | 41.6 | 69.95 | 54.22 | 43.26 |
meta-llama/Meta-Llama-3-8B-Instruct π | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 |
failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 π | 51.21 | 40.23 | 69.5 | 52.44 | 42.69 |
mlabonne/OrpoLlama-3-8B π | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 |
meta-llama/Meta-Llama-3-8B π | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |
π³ Model family tree
𧩠Configuration
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
π» Usage
!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"])
- Downloads last month
- 6
Model tree for jcorenday/Daredevil-8B-GPTQ
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard68.860
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.500
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard69.240
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard59.890
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.450
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard73.540