Instructions to use Kukedlc/NeuralSirKrishna-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kukedlc/NeuralSirKrishna-7b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Kukedlc/NeuralSirKrishna-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kukedlc/NeuralSirKrishna-7b")
model = AutoModelForCausalLM.from_pretrained("Kukedlc/NeuralSirKrishna-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kukedlc/NeuralSirKrishna-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kukedlc/NeuralSirKrishna-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kukedlc/NeuralSirKrishna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kukedlc/NeuralSirKrishna-7b

SGLang

How to use Kukedlc/NeuralSirKrishna-7b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Kukedlc/NeuralSirKrishna-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kukedlc/NeuralSirKrishna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Kukedlc/NeuralSirKrishna-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kukedlc/NeuralSirKrishna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kukedlc/NeuralSirKrishna-7b with Docker Model Runner:
```
docker model run hf.co/Kukedlc/NeuralSirKrishna-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🧞 NeuralSirKrishna-7b

👩‍💻 Try here!

Talking to Sir Neural Krishna 7b

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

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:

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."
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.
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.
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