Instructions to use OEvortex/HelpingAI-9B-200k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OEvortex/HelpingAI-9B-200k with Transformers:

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

pipe = pipeline("text-generation", model="OEvortex/HelpingAI-9B-200k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B-200k")
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-9B-200k")
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-9B-200k with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OEvortex/HelpingAI-9B-200k",
	filename="helpingai-9b-200k-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 OEvortex/HelpingAI-9B-200k 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-9B-200k:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OEvortex/HelpingAI-9B-200k: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-9B-200k:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OEvortex/HelpingAI-9B-200k: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-9B-200k:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OEvortex/HelpingAI-9B-200k: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-9B-200k:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OEvortex/HelpingAI-9B-200k:Q4_K_M

Use Docker

docker model run hf.co/OEvortex/HelpingAI-9B-200k:Q4_K_M

LM Studio
Jan

vLLM

How to use OEvortex/HelpingAI-9B-200k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OEvortex/HelpingAI-9B-200k"
# 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-9B-200k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OEvortex/HelpingAI-9B-200k:Q4_K_M

SGLang

How to use OEvortex/HelpingAI-9B-200k 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-9B-200k" \
    --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-9B-200k",
		"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-9B-200k" \
        --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-9B-200k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use OEvortex/HelpingAI-9B-200k with Ollama:
```
ollama run hf.co/OEvortex/HelpingAI-9B-200k:Q4_K_M
```

Unsloth Studio new

How to use OEvortex/HelpingAI-9B-200k 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-9B-200k 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-9B-200k 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-9B-200k to start chatting

Docker Model Runner
How to use OEvortex/HelpingAI-9B-200k with Docker Model Runner:
```
docker model run hf.co/OEvortex/HelpingAI-9B-200k:Q4_K_M
```

Lemonade

How to use OEvortex/HelpingAI-9B-200k with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OEvortex/HelpingAI-9B-200k:Q4_K_M

Run and chat with the model

lemonade run user.HelpingAI-9B-200k-Q4_K_M

List all available models

lemonade list

Abhaykoul commited on Jul 15, 2024

Commit

a02c2bd

verified ·

1 Parent(s): 2d6deef

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -10

README.md CHANGED Viewed

@@ -12,12 +12,12 @@ datasets:
 - OEvortex/EmotionalIntelligence-10K
 ---
-# HelpingAI-9B: Emotionally Intelligent Conversational AI
 ![logo](https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png)
 ## Overview
-HelpingAI-9B is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs.
 ## Objectives
 - Engage in open-ended dialogue while displaying emotional intelligence
@@ -25,16 +25,17 @@ HelpingAI-9B is a large language model designed for emotionally intelligent conv
 - Provide supportive, empathetic, and psychologically-grounded responses
 - Avoid insensitive, harmful, or unethical speech
 - Continuously improve emotional awareness and dialogue skills
 ## Methodology
-HelpingAI-9B is based on the HelpingAI series and further trained using:
 - Supervised learning on large dialogue datasets with emotional labeling
 - Reinforcement learning with a reward model favoring emotionally supportive responses
 - Constitution training to instill stable and beneficial objectives
 - Knowledge augmentation from psychological resources on emotional intelligence
 ## Emotional Quotient (EQ)
-HelpingAI-9B has achieved an impressive Emotional Quotient (EQ) of 89.23, surpassing almost all AI models in emotional intelligence. This EQ score reflects its advanced ability to understand and respond to human emotions in a supportive and empathetic manner.
 ![benchmarks](benchmark_performance_comparison.png)
@@ -43,11 +44,11 @@ HelpingAI-9B has achieved an impressive Emotional Quotient (EQ) of 89.23, surpas
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-# Let's bring in the big guns! Our super cool HelpingAI-9B model
-model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-9B").to("cuda")
 # We also need the special HelpingAI translator to understand our chats
-tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B")
 # This TextStreamer thingy is our secret weapon for super smooth conversation flow
 streamer = TextStreamer(tokenizer)
@@ -95,8 +96,8 @@ import os
 # 1. Download the model
-repo_id = "OEvortex/HelpingAI-9B"
-filename = "helpingai-9b.Q4_0.gguf"
 model_path = download_model(repo_id, filename, os.environ.get("hf_token"))
 # 2. Load the model
@@ -116,7 +117,7 @@ sampler = SamplerSettings(temp=0.7, top_p=0.9)  # Adjust these values as needed
 thread = Thread(model, custom_chatml, sampler=sampler)
 # 7. Start interacting with the model
-thread.interact(header="🌟 HelpingAI-9B: Emotionally Intelligent Conversational AI 🚀", color=True)
 ```
 ## Example Dialogue
   > Express joy and excitement about visiting a new place.

 - OEvortex/EmotionalIntelligence-10K
 ---
+# HelpingAI-9B-200k: Emotionally Intelligent Conversational AI with 200k context window
 ![logo](https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png)
 ## Overview
+HelpingAI-9B-200k is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs.
 ## Objectives
 - Engage in open-ended dialogue while displaying emotional intelligence
 - Provide supportive, empathetic, and psychologically-grounded responses
 - Avoid insensitive, harmful, or unethical speech
 - Continuously improve emotional awareness and dialogue skills
+- High Context length
 ## Methodology
+HelpingAI-9B-200k is based on the HelpingAI series and further trained using:
 - Supervised learning on large dialogue datasets with emotional labeling
 - Reinforcement learning with a reward model favoring emotionally supportive responses
 - Constitution training to instill stable and beneficial objectives
 - Knowledge augmentation from psychological resources on emotional intelligence
 ## Emotional Quotient (EQ)
+HelpingAI-9B-200k has achieved an impressive Emotional Quotient (EQ) of 89.23, surpassing almost all AI models in emotional intelligence. This EQ score reflects its advanced ability to understand and respond to human emotions in a supportive and empathetic manner.
 ![benchmarks](benchmark_performance_comparison.png)
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+# Let's bring in the big guns! Our super cool HelpingAI-9B-200k model
+model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-9B-200k-200k").to("cuda")
 # We also need the special HelpingAI translator to understand our chats
+tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B-200k-200k")
 # This TextStreamer thingy is our secret weapon for super smooth conversation flow
 streamer = TextStreamer(tokenizer)
 # 1. Download the model
+repo_id = "OEvortex/HelpingAI-9B-200k-200k"
+filename = "HelpingAI-9B-200k.Q4_0.gguf"
 model_path = download_model(repo_id, filename, os.environ.get("hf_token"))
 # 2. Load the model
 thread = Thread(model, custom_chatml, sampler=sampler)
 # 7. Start interacting with the model
+thread.interact(header="🌟 HelpingAI-9B-200k: Emotionally Intelligent Conversational AI 🚀", color=True)
 ```
 ## Example Dialogue
   > Express joy and excitement about visiting a new place.