Instructions to use HelpingAI/HelpingAI2-6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HelpingAI/HelpingAI2-6B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HelpingAI/HelpingAI2-6B",
	filename="helpingai-6b-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 HelpingAI/HelpingAI2-6B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HelpingAI/HelpingAI2-6B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HelpingAI/HelpingAI2-6B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HelpingAI/HelpingAI2-6B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HelpingAI/HelpingAI2-6B: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 HelpingAI/HelpingAI2-6B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HelpingAI/HelpingAI2-6B: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 HelpingAI/HelpingAI2-6B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HelpingAI/HelpingAI2-6B:Q4_K_M

Use Docker

docker model run hf.co/HelpingAI/HelpingAI2-6B:Q4_K_M

LM Studio
Jan

vLLM

How to use HelpingAI/HelpingAI2-6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HelpingAI/HelpingAI2-6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HelpingAI/HelpingAI2-6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HelpingAI/HelpingAI2-6B:Q4_K_M

Ollama
How to use HelpingAI/HelpingAI2-6B with Ollama:
```
ollama run hf.co/HelpingAI/HelpingAI2-6B:Q4_K_M
```

Unsloth Studio new

How to use HelpingAI/HelpingAI2-6B 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 HelpingAI/HelpingAI2-6B 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 HelpingAI/HelpingAI2-6B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HelpingAI/HelpingAI2-6B to start chatting

Docker Model Runner
How to use HelpingAI/HelpingAI2-6B with Docker Model Runner:
```
docker model run hf.co/HelpingAI/HelpingAI2-6B:Q4_K_M
```

Lemonade

How to use HelpingAI/HelpingAI2-6B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HelpingAI/HelpingAI2-6B:Q4_K_M

Run and chat with the model

lemonade run user.HelpingAI2-6B-Q4_K_M

List all available models

lemonade list

Abhaykoul commited on Aug 5, 2024

Commit

193dea9

verified ·

1 Parent(s): e027fc4

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ HelpingAI-6B has achieved an impressive Emotional Quotient (EQ) of 91.57, making
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-# Load the HelpingAI-3B-coder model
 model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-6B", trust_remote_code=True)
 # Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-6B", trust_remote_code=True)
@@ -75,8 +75,6 @@ outputs = model.generate(
     eos_token_id=tokenizer.eos_token_id,
 )
-# Decode the generated text
-output = tokenizer.decode(generated_text[0], skip_special_tokens=True)
 response = outputs[0][inputs.shape[-1]:]
 print(tokenizer.decode(response, skip_special_tokens=True))

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+# Load the HelpingAI-6B model
 model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-6B", trust_remote_code=True)
 # Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-6B", trust_remote_code=True)
     eos_token_id=tokenizer.eos_token_id,
 )
 response = outputs[0][inputs.shape[-1]:]
 print(tokenizer.decode(response, skip_special_tokens=True))