Instructions to use LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0 with Transformers:

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

pipe = pipeline("text-generation", model="LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0")
model = AutoModelForCausalLM.from_pretrained("LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0

SGLang

How to use LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0 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 "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0 with Docker Model Runner:
```
docker model run hf.co/LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

https://github.com/spydaz

Currently undegoing Fine tuning ! as this model contains all Previous models !

This model contains many hidden tensors : As it was emrged with many lora adapter for various task such as vision and sound . The problem was that for some reason i could not get the extra heads to show up like other models. such as the llava model ... i suppose this model can change the config.json to be a llava model and yes ! it works! ie it can think and has hidden think heads ? but you need to config it up !, It has vision heads but also i could not set the config up ! so hidden talents: It was also merged with the mothers of these models for QUiet(thoughts) and (llava vision etc ) so the tensors are there . i just did not understand how to fine tne the addtional funcitonalitys. as they need a single trainign example to populate the hidden tensor hence te merges. and yet when the model is put in train mode , ie by setting the model after loading to model.TRAIN ... the tensors apear waiting for training so just add a peft and start the training!

THIS VERSION HAS BEEN UPDATED TO INCLUDE CYBERBRAIN ! (Hidden Tensors)

Extended capabilities:

mistralai/Mistral-7B-Instruct-v0.1 - Prime-Base
ChaoticNeutrals/Eris-LelantaclesV2-7b - role play
ChaoticNeutrals/Eris_PrimeV3-Vision-7B - vision
rvv-karma/BASH-Coder-Mistral-7B - coding
Locutusque/Hercules-3.1-Mistral-7B - Unhinging
KoboldAI/Mistral-7B-Erebus-v3 - NSFW
Locutusque/Hyperion-2.1-Mistral-7B - CHAT
Severian/Nexus-IKM-Mistral-7B-Pytorch - Thinking
NousResearch/Hermes-2-Pro-Mistral-7B - Generalizing
mistralai/Mistral-7B-Instruct-v0.2 - BASE
Nitral-AI/ProdigyXBioMistral_7B - medical
Nitral-AI/Infinite-Mika-7b - 128k - Context Expansion enforcement
Nous-Yarn-Mistral-7b-128k - 128k - Context Expansion
yanismiraoui/Yarn-Mistral-7b-128k-sharded
ChaoticNeutrals/Eris_Prime-V2-7B - Roleplay

This Expert is a companon to the MEGA_MIND 24b CyberSeries represents a groundbreaking leap in the realm of language models, integrating a diverse array of expert models into a unified framework. At its core lies the Mistral-7B-Instruct-v0.2, a refined instructional model designed for versatility and efficiency.

Enhanced with an expanded context window and advanced routing mechanisms, the Mistral-7B-Instruct-v0.2 exemplifies the power of Mixture of Experts, allowing seamless integration of specialized sub-models. This architecture facilitates unparalleled performance and scalability, enabling the CyberSeries to tackle a myriad of tasks with unparalleled speed and accuracy.

Among its illustrious sub-models, the OpenOrca - Mistral-7B-8k shines as a testament to fine-tuning excellence, boasting top-ranking performance in its class. Meanwhile, the Hermes 2 Pro introduces cutting-edge capabilities such as Function Calling and JSON Mode, catering to diverse application needs.

Driven by Reinforcement Learning from AI Feedback, the Starling-LM-7B-beta demonstrates remarkable adaptability and optimization, while the Phi-1.5 Transformer model stands as a beacon of excellence across various domains, from common sense reasoning to medical inference.

With models like BioMistral tailored specifically for medical applications and Nous-Yarn-Mistral-7b-128k excelling in handling long-context data, the MEGA_MIND 24b CyberSeries emerges as a transformative force in the landscape of language understanding and artificial intelligence.

Experience the future of language models with the MEGA_MIND 24b CyberSeries, where innovation meets performance, and possibilities are limitless.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: LeroyDyer/Mixtral_AI_Cyber_Dolphin_2.0
    parameters:
      density: [0.256, 0.512, 0.128] # density gradient
      weight: 0.382
  - model: LeroyDyer/Mixtral_AI_CyberLAW
    parameters:
      density: 0.382
      weight: [0.256, 0.128, 0.256, 0.128] # weight gradient
  - model: LeroyDyer/Mixtral_AI_CyberBrain_3_0
    parameters:
      density: 0.382
      weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
  - model: LeroyDyer/Mixtral_AI_Multi_TEST
    parameters:
      density: 0.382
      weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
  - model: LeroyDyer/Mixtral_AI_Cyber_5.0
    parameters:
      density: 0.382
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model:  LeroyDyer/Mixtral_AI_Cyber_Dolphin_2.0
parameters:
  normalize: true
  int8_mask: true
dtype: float16