Instructions to use Z3R6X/gpt4all_dpo_instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Z3R6X/gpt4all_dpo_instruct with Transformers:

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

pipe = pipeline("text-generation", model="Z3R6X/gpt4all_dpo_instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Z3R6X/gpt4all_dpo_instruct")
model = AutoModelForCausalLM.from_pretrained("Z3R6X/gpt4all_dpo_instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Z3R6X/gpt4all_dpo_instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Z3R6X/gpt4all_dpo_instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Z3R6X/gpt4all_dpo_instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Z3R6X/gpt4all_dpo_instruct

SGLang

How to use Z3R6X/gpt4all_dpo_instruct 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 "Z3R6X/gpt4all_dpo_instruct" \
    --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": "Z3R6X/gpt4all_dpo_instruct",
		"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 "Z3R6X/gpt4all_dpo_instruct" \
        --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": "Z3R6X/gpt4all_dpo_instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Z3R6X/gpt4all_dpo_instruct with Docker Model Runner:
```
docker model run hf.co/Z3R6X/gpt4all_dpo_instruct
```

Question answering model finetuned from GPT4All-J v1.3 with Direct Preference Optimization.
Dataset: Dahoas/instruct-synthetic-prompt-responses.

The model was finetuned with the following promt:
"Answer the following question in context:\n\nQuestion: " + samples["prompt"] + " Answer: "
It should be benefical to use the same or a similar prompt for inference.

An increase in performance compared to GPT4All-J v1.3 was observed when using two-shot Chain-of-Thought prompting.

HellaSwag	WinoGrande	BooLQ	ARC-c
62.37%	63.3%	65.2%	32.76%

Downloads last month: 9

Dataset used to train Z3R6X/gpt4all_dpo_instruct

Paper for Z3R6X/gpt4all_dpo_instruct

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Paper • 2305.18290 • Published May 29, 2023 • 68