Instructions to use zeroblu3/NeuralPoppy-EVO-L3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zeroblu3/NeuralPoppy-EVO-L3-8B with Transformers:

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

pipe = pipeline("text-generation", model="zeroblu3/NeuralPoppy-EVO-L3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zeroblu3/NeuralPoppy-EVO-L3-8B")
model = AutoModelForCausalLM.from_pretrained("zeroblu3/NeuralPoppy-EVO-L3-8B")
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]:]))

Inference
Local Apps Settings

vLLM

How to use zeroblu3/NeuralPoppy-EVO-L3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zeroblu3/NeuralPoppy-EVO-L3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zeroblu3/NeuralPoppy-EVO-L3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zeroblu3/NeuralPoppy-EVO-L3-8B

SGLang

How to use zeroblu3/NeuralPoppy-EVO-L3-8B 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 "zeroblu3/NeuralPoppy-EVO-L3-8B" \
    --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": "zeroblu3/NeuralPoppy-EVO-L3-8B",
		"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 "zeroblu3/NeuralPoppy-EVO-L3-8B" \
        --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": "zeroblu3/NeuralPoppy-EVO-L3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zeroblu3/NeuralPoppy-EVO-L3-8B with Docker Model Runner:
```
docker model run hf.co/zeroblu3/NeuralPoppy-EVO-L3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A megamerge of 10 selected models merged with the "Model Stock" method, using Poppy Porpoise 0.72 as a base. Pretty good at all tasks, strong focus on RP and storytelling, uncensored (does pretty much everything if you ask it to), large knowledge base.

ST Presets in the repo.

Imatrix Quants available here https://huggingface.co/zeroblu3/NeuralPoppy-EVO-L3-imat.GGUF

Downloads last month: 18

Safetensors

Model size

8B params

Tensor type

F16

Model tree for zeroblu3/NeuralPoppy-EVO-L3-8B

Merges

1 model

Quantizations

3 models

zeroblu3
/

NeuralPoppy-EVO-L3-8B

Model tree for zeroblu3/NeuralPoppy-EVO-L3-8B

Spaces using zeroblu3/NeuralPoppy-EVO-L3-8B 8