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

Libraries

How to use OEvortex/HelpingAI-flash with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-flash")
model = AutoModelForMultimodalLM.from_pretrained("OEvortex/HelpingAI-flash")
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]:]))

llama-cpp-python

How to use OEvortex/HelpingAI-flash with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OEvortex/HelpingAI-flash",
	filename="helpingai-flash-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use OEvortex/HelpingAI-flash with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/OEvortex/HelpingAI-flash:Q4_K_M

LM Studio
Jan

vLLM

How to use OEvortex/HelpingAI-flash with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OEvortex/HelpingAI-flash:Q4_K_M

SGLang

How to use OEvortex/HelpingAI-flash 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 "OEvortex/HelpingAI-flash" \
    --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": "OEvortex/HelpingAI-flash",
		"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 "OEvortex/HelpingAI-flash" \
        --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": "OEvortex/HelpingAI-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use OEvortex/HelpingAI-flash with Ollama:
```
ollama run hf.co/OEvortex/HelpingAI-flash:Q4_K_M
```

Unsloth Studio

How to use OEvortex/HelpingAI-flash 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 OEvortex/HelpingAI-flash 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 OEvortex/HelpingAI-flash to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use OEvortex/HelpingAI-flash with Docker Model Runner:
```
docker model run hf.co/OEvortex/HelpingAI-flash:Q4_K_M
```

Lemonade

How to use OEvortex/HelpingAI-flash with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OEvortex/HelpingAI-flash:Q4_K_M

Run and chat with the model

lemonade run user.HelpingAI-flash-Q4_K_M

List all available models

lemonade list

Abhaykoul commited on Jul 19, 2024

Commit

3799ee0

verified ·

1 Parent(s): cbef637

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ datasets:
 # HelpingAI-flash: Emotionally Intelligent Conversational AI for All Devices
-![logo](https://huggingface.co/OEvortex/HelpingAI-flash/resolve/main/HelpingAI.png)
 ## Overview
 HelpingAI-flash is a versatile 2B parameter language model designed to deliver emotionally intelligent conversational interactions across all devices, including smartphones. It is engineered to engage users with empathy, understanding, and supportive dialogue, adapting seamlessly to various contexts and platforms. This model strives to offer a compassionate AI companion that resonates with users’ emotional needs and provides meaningful interactions wherever they are.
@@ -35,7 +35,7 @@ HelpingAI-flash builds upon the HelpingAI series and incorporates:
 - Integration of knowledge from psychological resources on emotional intelligence
 ## Emotional Quotient (EQ)
-HelpingAI-flash boasts an impressive Emotional Quotient (EQ) score of 85.23, highlighting its superior capability to understand and respond to human emotions in a caring and supportive manner.
 ![benchmarks](benchmark_performance_comparison.png)

 # HelpingAI-flash: Emotionally Intelligent Conversational AI for All Devices
+![logo](https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png)
 ## Overview
 HelpingAI-flash is a versatile 2B parameter language model designed to deliver emotionally intelligent conversational interactions across all devices, including smartphones. It is engineered to engage users with empathy, understanding, and supportive dialogue, adapting seamlessly to various contexts and platforms. This model strives to offer a compassionate AI companion that resonates with users’ emotional needs and provides meaningful interactions wherever they are.
 - Integration of knowledge from psychological resources on emotional intelligence
 ## Emotional Quotient (EQ)
+HelpingAI-flash boasts an impressive Emotional Quotient (EQ) score of xx.xx, highlighting its superior capability to understand and respond to human emotions in a caring and supportive manner.
 ![benchmarks](benchmark_performance_comparison.png)