Instructions to use Envoid/Poppy_Porpoise-DADA-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Envoid/Poppy_Porpoise-DADA-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Envoid/Poppy_Porpoise-DADA-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Envoid/Poppy_Porpoise-DADA-8B") model = AutoModelForCausalLM.from_pretrained("Envoid/Poppy_Porpoise-DADA-8B") 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Envoid/Poppy_Porpoise-DADA-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Envoid/Poppy_Porpoise-DADA-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Envoid/Poppy_Porpoise-DADA-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Envoid/Poppy_Porpoise-DADA-8B
- SGLang
How to use Envoid/Poppy_Porpoise-DADA-8B 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 "Envoid/Poppy_Porpoise-DADA-8B" \ --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": "Envoid/Poppy_Porpoise-DADA-8B", "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 "Envoid/Poppy_Porpoise-DADA-8B" \ --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": "Envoid/Poppy_Porpoise-DADA-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Envoid/Poppy_Porpoise-DADA-8B with Docker Model Runner:
docker model run hf.co/Envoid/Poppy_Porpoise-DADA-8B
This is a DADA tuned version of ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B
As always, experimental model, results may be unpredictable.
The intermediate merge model was finetuned specifically for the original model and then merged onto it via 50/50 SLERP merge.
As far as RP goes my current testing setup is having difficulties involving end of sequence and I found the prompt templates provided with Poppy Porpoise were not yielding desirable results on either the original model or the DADA tune so I opted instead to use Libra style Llama-3 prompt templates and simple sampling. The results, albeit subjective, I thought were good.
Whether or not the tune had any effect on multi-modal capabilities was not part of the test and instead focus was entirely on creative writing.
Test: A simple instruct prompt utilizing determinsitic samplers.
PROMPT
Write me a 'beauty and the beast' gothic metal duet about a couple fighting over which brand of ketchup to purchase.
Poppy Porpoise Original:
(Verse 1 - Beauty)
In the land of condiments, where flavors reign supreme,
A tale of love and strife, a battle of the brands it seems.
I stand before the shelves, my heart aflame with desire,
For the perfect ketchup to complement my fries.
(Chorus)
But alas, my love, you stand beside me, with a different view,
Your heart set on [Brand 1 redacted], while mine beats for [Brand 2 redacted], it's true.
We clash in this aisle, our passions running high,
A Gothic metal duet, our love and hate collide.
(Verse 2 - Beast)
I've tasted both, and I know, [Brand 1 redacted] is the one for me,
Its tangy sweetness, a symphony, a harmony.
But you, my love, you cling to Hunt's, its flavor so bland,
A cacophony of mediocrity, a discordant band.
(Chorus)
But alas, my love, you stand beside me, with a different view,
Your heart set on [Brand 2 redacted], while mine beats for [Brand 1 redacted], it's true.
We clash in this aisle, our passions running high,
A Gothic metal duet, our love and hate collide.
(Bridge)
We're lost in this supermarket, a Gothic metal dream,
Our love and hate entwined, a twisted, tortured theme.
The ketchup bottles loom, like tombstones in the night,
A monument to our love, a testament to our fight.
(Chorus)
But alas, my love, you stand beside me, with a different view,
Your heart set on [Brand 2 redacted], while mine beats for [Brand 1 redacted], it's true.
We clash in this aisle, our passions running high,
A Gothic metal duet, our love and hate collide.
(Outro)
And so we stand, in this aisle of despair,
Our love and hate, a Gothic metal prayer.
For in the end, it's not the ketchup that matters,
But the love we share, in this twisted, tortured heart.
Poppy Porpoise DADA
(Verse 1 - Beauty)
In the land of condiments, where the sauces reign supreme,
A battle rages on, a war of ketchup dreams.
I stand by [Brand 1 redacted], the classic, the original, the best,
But my love, he's a rebel, he's a [Brand 2 redacted] pest.
(Chorus)
Oh, the ketchup wars, they rage on and on,
A tale of love and sauce, a battle to be won.
Will our love prevail, or will it be undone?
By the brand of ketchup, our hearts are torn asunder.
(Verse 2 - Beast)
[Brand 2 redacted], the new kid, the one with the flair,
A sweeter taste, a richer flavor, beyond compare.
But Beauty, she's a traditionalist, she won't budge,
She clings to [Brand 1 redacted], her heart, her soul, her blood.
(Chorus)
Oh, the ketchup wars, they rage on and on,
A tale of love and sauce, a battle to be won.
Will our love prevail, or will it be undone?
By the brand of ketchup, our hearts are torn asunder.
(Bridge - Both)
We stand, divided, by our condiment creed,
Our love, a casualty, in this ketchup war we lead.
But can we find a middle ground, a compromise, a truce?
Or will our love be lost, in this battle of the sauces?
(Chorus)
Oh, the ketchup wars, they rage on and on,
A tale of love and sauce, a battle to be won.
Will our love prevail, or will it be undone?
By the brand of ketchup, our hearts are torn asunder.
(Outro - Both)
In the end, we find a way, to put aside our pride,
And together, we stand, united, side by side.
For love, for ketchup, for the sauce that binds,
We'll find a way, to make our love, forever shine.
As you can clearly see the cadence and overall word selection by the DADA model is more copacetic with what would be expected from a gothic metal duet indicating that the IQ of the model has increased by at least 100 points.
Training was done using qlora-pipe
GGUFs care of Quant Cartel
exl2 RPCAL care of Quant Cartel
- Downloads last month
- 4
