Hugging Face's logo

RichardErkhov
/
mlabonne_-_Daredevil-8B-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
mlabonne_-_Daredevil-8B-gguf / README.md
RichardErkhov's picture
RichardErkhov
uploaded readme
e5acfe9 verified
preview code
|
raw
history blame contribute delete
12.6 kB

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Daredevil-8B - GGUF

Name Quant method Size
Daredevil-8B.Q2_K.gguf Q2_K 2.96GB
Daredevil-8B.IQ3_XS.gguf IQ3_XS 3.28GB
Daredevil-8B.IQ3_S.gguf IQ3_S 3.43GB
Daredevil-8B.Q3_K_S.gguf Q3_K_S 3.41GB
Daredevil-8B.IQ3_M.gguf IQ3_M 3.52GB
Daredevil-8B.Q3_K.gguf Q3_K 3.74GB
Daredevil-8B.Q3_K_M.gguf Q3_K_M 3.74GB
Daredevil-8B.Q3_K_L.gguf Q3_K_L 4.03GB
Daredevil-8B.IQ4_XS.gguf IQ4_XS 4.18GB
Daredevil-8B.Q4_0.gguf Q4_0 4.34GB
Daredevil-8B.IQ4_NL.gguf IQ4_NL 4.38GB
Daredevil-8B.Q4_K_S.gguf Q4_K_S 4.37GB
Daredevil-8B.Q4_K.gguf Q4_K 4.58GB
Daredevil-8B.Q4_K_M.gguf Q4_K_M 4.58GB
Daredevil-8B.Q4_1.gguf Q4_1 4.78GB
Daredevil-8B.Q5_0.gguf Q5_0 5.21GB
Daredevil-8B.Q5_K_S.gguf Q5_K_S 5.21GB
Daredevil-8B.Q5_K.gguf Q5_K 5.34GB
Daredevil-8B.Q5_K_M.gguf Q5_K_M 5.34GB
Daredevil-8B.Q5_1.gguf Q5_1 5.65GB
Daredevil-8B.Q6_K.gguf Q6_K 6.14GB
Daredevil-8B.Q8_0.gguf Q8_0 7.95GB

Original model description:

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

image/jpeg

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:

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.

This is a censored model. For an uncensored version, see mlabonne/Daredevil-8B-abliterated.

Tested on LM Studio using the "Llama 3" preset.

⚡ Quantization

🏆 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).

image/png

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 📄 55.87 44.13 73.52 59.05 46.77
mlabonne/Daredevil-8B-abliterated 📄 55.06 43.29 73.33 57.47 46.17
mlabonne/Llama-3-8B-Instruct-abliterated-dpomix 📄 52.26 41.6 69.95 54.22 43.26
meta-llama/Meta-Llama-3-8B-Instruct 📄 51.34 41.22 69.86 51.65 42.64
failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 📄 51.21 40.23 69.5 52.44 42.69
mlabonne/OrpoLlama-3-8B 📄 48.63 34.17 70.59 52.39 37.36
meta-llama/Meta-Llama-3-8B 📄 45.42 31.1 69.95 43.91 36.7

🌳 Model family tree

image/png

🧩 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

💻 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"])