metadata

license: apache-2.0
tags:
  - moe

Beyonder-4x7B-v2

This model is a Mixture of Experts (MoE) made with mergekit (mixtral branch). It uses the following base models:

🏆 Evaluation

Beyonder-4x7B-v2 is competitive with Mixtral-8x7B-Instruct-v0.1 on the Open LLM Leaderboard, while only having 4 experts instead of 8.

It also displays a significant improvement over the individual experts.

It also performs very well compared to other models on Nous benchmark suite. It's almost as good as the best Yi-34B fine-tune, which is a much bigger model: 24.2B parameters + only two experts are selected during inference (so ~12B) vs. 34B param.

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Beyonder-4x7B-v2	45.29	75.95	60.86	46.4	57.13
NeuralHermes-2.5-Mistral-7B	43.67	73.24	55.37	41.76	53.51
OpenHermes-2.5-Mistral-7B	42.75	72.99	52.99	40.94	52.42
Nous-Hermes-2-SOLAR-10.7B	47.79	74.69	55.92	44.84	55.81
Nous-Hermes-2-Yi-34B	50.27	76.00	60.34	46.69	58.33

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	23.62	±	2.67
		acc_norm	23.62	±	2.67
agieval_logiqa_en	0	acc	41.47	±	1.93
		acc_norm	43.01	±	1.94
agieval_lsat_ar	0	acc	23.04	±	2.78
		acc_norm	23.48	±	2.80
agieval_lsat_lr	0	acc	51.57	±	2.22
		acc_norm	52.94	±	2.21
agieval_lsat_rc	0	acc	64.31	±	2.93
		acc_norm	64.68	±	2.92
agieval_sat_en	0	acc	79.13	±	2.84
		acc_norm	79.13	±	2.84
agieval_sat_en_without_passage	0	acc	43.20	±	3.46
		acc_norm	43.20	±	3.46
agieval_sat_math	0	acc	34.55	±	3.21
		acc_norm	32.27	±	3.16

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	61.86	±	1.42
		acc_norm	64.51	±	1.40
arc_easy	0	acc	85.06	±	0.73
		acc_norm	82.45	±	0.78
boolq	1	acc	88.35	±	0.56
hellaswag	0	acc	68.04	±	0.47
		acc_norm	85.12	±	0.36
openbookqa	0	acc	37.80	±	2.17
		acc_norm	48.60	±	2.24
piqa	0	acc	83.08	±	0.87
		acc_norm	83.95	±	0.86
winogrande	0	acc	78.69	±	1.15

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	44.55	±	1.74
		mc2	60.86	±	1.57

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	58.95	±	3.58
bigbench_date_understanding	0	multiple_choice_grade	66.40	±	2.46
bigbench_disambiguation_qa	0	multiple_choice_grade	48.84	±	3.12
bigbench_geometric_shapes	0	multiple_choice_grade	22.56	±	2.21
		exact_str_match	13.37	±	1.80
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	30.40	±	2.06
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	20.57	±	1.53
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	52.00	±	2.89
bigbench_movie_recommendation	0	multiple_choice_grade	44.40	±	2.22
bigbench_navigate	0	multiple_choice_grade	52.10	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	69.75	±	1.03
bigbench_ruin_names	0	multiple_choice_grade	55.36	±	2.35
bigbench_salient_translation_error_detection	0	multiple_choice_grade	23.65	±	1.35
bigbench_snarks	0	multiple_choice_grade	77.35	±	3.12
bigbench_sports_understanding	0	multiple_choice_grade	73.02	±	1.41
bigbench_temporal_sequences	0	multiple_choice_grade	46.80	±	1.58
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	22.08	±	1.17
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	19.03	±	0.94
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	52.00	±	2.89

🧩 Configuration

base_model: mlabonne/Marcoro14-7B-slerp
experts:
  - source_model: openchat/openchat-3.5-1210
    positive_prompts:
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
  - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
    positive_prompts:
    - "code"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
  - source_model: maywell/PiVoT-0.1-Starling-LM-RP
    positive_prompts:
    - "storywriting"
    - "write"
    - "scene"
    - "story"
    - "character"
  - source_model: WizardLM/WizardMath-7B-V1.1
    positive_prompts:
    - "reason"
    - "math"
    - "mathematics"
    - "solve"
    - "count"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Beyonder-4x7B-v2"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])