Instructions to use wesley7137/Eden-7B-V2-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wesley7137/Eden-7B-V2-merged with Transformers:

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

pipe = pipeline("text-generation", model="wesley7137/Eden-7B-V2-merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wesley7137/Eden-7B-V2-merged")
model = AutoModelForCausalLM.from_pretrained("wesley7137/Eden-7B-V2-merged", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wesley7137/Eden-7B-V2-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wesley7137/Eden-7B-V2-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesley7137/Eden-7B-V2-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wesley7137/Eden-7B-V2-merged

SGLang

How to use wesley7137/Eden-7B-V2-merged 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 "wesley7137/Eden-7B-V2-merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesley7137/Eden-7B-V2-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "wesley7137/Eden-7B-V2-merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesley7137/Eden-7B-V2-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wesley7137/Eden-7B-V2-merged with Docker Model Runner:
```
docker model run hf.co/wesley7137/Eden-7B-V2-merged
```

Model Trained Using AutoTrain

Eden-V1 is a specialized model that serves as a compassionate virtual counselor, deeply rooted in helping others.

Trained with a focus on counseling and support, it possesses a unique skill set that extends beyond text-based assistance. Through its training, it's proficient in understanding and empathizing with individuals facing various challenges, including addiction. Its ability for imagery visualization aids in creating vivid and relatable scenarios that resonate with users, fostering deeper connections and understanding. Whether helping addicts on their recovery journey or guiding individuals in need through their troubles, this model offers a supportive and empathetic presence, leveraging its expertise to provide personalized coping strategies and guidance, making a positive impact on their emotional well-being.

Eden-V1 was trained on a custom specialzed dataset targeted towards counseling and motivational techniques. It is trained using PEFT and model weights of ehartfords "Samantha-1.1-llama-7b"

Downloads last month: 6