Instructions to use Abhaykoul/HelpingAI2-4x6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abhaykoul/HelpingAI2-4x6B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Abhaykoul/HelpingAI2-4x6B",
	filename="helpingai2-4x6b-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Abhaykoul/HelpingAI2-4x6B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abhaykoul/HelpingAI2-4x6B:Q4_K_M

Use Docker

docker model run hf.co/Abhaykoul/HelpingAI2-4x6B:Q4_K_M

LM Studio
Jan

vLLM

How to use Abhaykoul/HelpingAI2-4x6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abhaykoul/HelpingAI2-4x6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abhaykoul/HelpingAI2-4x6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abhaykoul/HelpingAI2-4x6B:Q4_K_M

Ollama
How to use Abhaykoul/HelpingAI2-4x6B with Ollama:
```
ollama run hf.co/Abhaykoul/HelpingAI2-4x6B:Q4_K_M
```

Unsloth Studio new

How to use Abhaykoul/HelpingAI2-4x6B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Abhaykoul/HelpingAI2-4x6B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Abhaykoul/HelpingAI2-4x6B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abhaykoul/HelpingAI2-4x6B to start chatting

Docker Model Runner
How to use Abhaykoul/HelpingAI2-4x6B with Docker Model Runner:
```
docker model run hf.co/Abhaykoul/HelpingAI2-4x6B:Q4_K_M
```

Lemonade

How to use Abhaykoul/HelpingAI2-4x6B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abhaykoul/HelpingAI2-4x6B:Q4_K_M

Run and chat with the model

lemonade run user.HelpingAI2-4x6B-Q4_K_M

List all available models

lemonade list

HelpingAI2-4x6B : Emotionally Intelligent Conversational AI

Usage Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the HelpingAI2-4x6B  model
model = AutoModelForCausalLM.from_pretrained("Abhaykoul/HelpingAI2-4x6B ", trust_remote_code=True)
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("Abhaykoul/HelpingAI2-4x6B ", trust_remote_code=True)


# Define the chat input
chat = [
    { "role": "system", "content": "You are HelpingAI, an emotional AI. Always answer my questions in the HelpingAI style." },
    { "role": "user", "content": "I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone." }
]

inputs = tokenizer.apply_chat_template(
    chat,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)


# Generate text
outputs = model.generate(
    inputs,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
    eos_token_id=tokenizer.eos_token_id, 
)


response = outputs[0][inputs.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Downloads last month: 18

Safetensors

Model size

17B params

Tensor type

F16

Abhaykoul
/

HelpingAI2-4x6B

HelpingAI2-4x6B : Emotionally Intelligent Conversational AI

Usage Code

Datasets used to train Abhaykoul/HelpingAI2-4x6B