NeuralSirKrishna-7b/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
apache-2.0	merge mergekit lazymergekit Kukedlc/NeuralKrishna-7B-v3 Kukedlc/NeuralMarioMonarch-7B-slerp liminerity/M7-7b	Kukedlc/NeuralKrishna-7B-v3 Kukedlc/NeuralMarioMonarch-7B-slerp liminerity/M7-7b	name results NeuralSirKrishna-7b task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 73.72 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 89.05 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 64.63 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 75.6 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 85.32 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 71.27 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b Open LLM Leaderboard

🧞 NeuralSirKrishna-7b

👩‍💻 Try here!

Talking to Sir Neural Krishna 7b

NeuralKrishna-7B-v4 is a merge of the following models using LazyMergekit:

• Kukedlc/NeuralKrishna-7B-v3
• Kukedlc/NeuralMarioMonarch-7B-slerp
• liminerity/M7-7b

Chat

• User: Create an advanced theory about the origin of life on earth that is new, innovative, and disruptive, totally new with no resemblance to anything else but at the same time that can be real.

• System: I. The Symbiotic Cosmic Initiation Hypothesis (SCIH)

To propose a groundbreaking and disruptive theory about the origin of life on Earth, let's envision an interconnected web of cosmic events that transcends conventional understanding. The Symbiotic Cosmic Initiation Hypothesis (SCIH) posits that life didn't arise from a singular event or molecular accident but rather from a complex, multifaceted interplay between extraterrestrial entities and our planet's nascent environment. Here are its core tenets:

1. Prebiotic Symbionts: SCIH rejects the notion of a solitary "building block" or "spark of life." Instead, it postulates that prebiotic symbionts – self-replicating, organic-inorganic complexes – arrived on Earth from space via meteorites and comets. These symbionts, composed of a diverse array of biomolecules and mineral catalysts, were the products of extraterrestrial ecosystems or "astrobiomes."

2. Astrobiome Cross-Fertilization: The constant exchange of matter between our solar system's planets and asteroid belts facilitated the transfer of these prebiotic symbionts across vast distances. This cosmic symbiosis allowed for the intermingling of genetic and catalytic material, fostering evolutionary innovation and adaptability among these extraterrestrial life-forms.

3. Terrestrial Integration and Adaptation: Upon impacting Earth's surface, these prebiotic symbionts began to integrate with our planet's pre-existing chemical milieu. The resulting synergy between Earth-born and extraterrestrial biomolecules accelerated the formation of more complex organic structures, eventually leading to protocells – rudimentary, self-enclosed systems capable of rudimentary metabolism and replication.

4. The Catalytic Gaian Boost: As Earth's early atmosphere evolved to become more hospitable to life, a positive feedback loop between these protocells and our planet's environment ensued. The emergence of photosynthesis and other metabolic processes contributed to the creation of a self-regulating, life-nurturing environment – what we now call the Ga

🧩 Configuration

models:
  - model: Kukedlc/NeuralKrishna-7B-v3
    # no parameters necessary for base model
  - model: Kukedlc/NeuralKrishna-7B-v3
    parameters:
      density: 0.65
      weight: 0.36
  - model: Kukedlc/NeuralMarioMonarch-7B-slerp
    parameters:
      density: 0.6
      weight: 0.34
  - model: liminerity/M7-7b
    parameters:
      density: 0.4
      weight: 0.3
merge_method: dare_ties
base_model: Kukedlc/NeuralKrishna-7B-v3
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/NeuralSirKrishna-7b"
messages = [{"role": "user", "content": """Create an advanced theory about the origin of life on earth that is new,
innovative, and disruptive, totally new with no resemblance to anything else but at the same time that can be real."""}]

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"])

🍃 Family models:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.60
AI2 Reasoning Challenge (25-Shot)	73.72
HellaSwag (10-Shot)	89.05
MMLU (5-Shot)	64.63
TruthfulQA (0-shot)	75.60
Winogrande (5-shot)	85.32
GSM8k (5-shot)	71.27