Instructions to use wesleysimplicio/Simplicio-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wesleysimplicio/Simplicio-27B with Transformers:

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

pipe = pipeline("text-generation", model="wesleysimplicio/Simplicio-27B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("wesleysimplicio/Simplicio-27B")
model = AutoModelForMultimodalLM.from_pretrained("wesleysimplicio/Simplicio-27B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wesleysimplicio/Simplicio-27B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wesleysimplicio/Simplicio-27B:BF16
# Run inference directly in the terminal:
llama cli -hf wesleysimplicio/Simplicio-27B:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wesleysimplicio/Simplicio-27B:BF16
# Run inference directly in the terminal:
llama cli -hf wesleysimplicio/Simplicio-27B:BF16

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 wesleysimplicio/Simplicio-27B:BF16
# Run inference directly in the terminal:
./llama-cli -hf wesleysimplicio/Simplicio-27B:BF16

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 wesleysimplicio/Simplicio-27B:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wesleysimplicio/Simplicio-27B:BF16

Use Docker

docker model run hf.co/wesleysimplicio/Simplicio-27B:BF16

LM Studio
Jan

vLLM

How to use wesleysimplicio/Simplicio-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wesleysimplicio/Simplicio-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesleysimplicio/Simplicio-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wesleysimplicio/Simplicio-27B:BF16

SGLang

How to use wesleysimplicio/Simplicio-27B 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 "wesleysimplicio/Simplicio-27B" \
    --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": "wesleysimplicio/Simplicio-27B",
		"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 "wesleysimplicio/Simplicio-27B" \
        --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": "wesleysimplicio/Simplicio-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use wesleysimplicio/Simplicio-27B with Ollama:
```
ollama run hf.co/wesleysimplicio/Simplicio-27B:BF16
```
Unsloth Desktop

How to use wesleysimplicio/Simplicio-27B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesleysimplicio/Simplicio-27B:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "wesleysimplicio/Simplicio-27B:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use wesleysimplicio/Simplicio-27B with Docker Model Runner:
```
docker model run hf.co/wesleysimplicio/Simplicio-27B:BF16
```

Lemonade

How to use wesleysimplicio/Simplicio-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wesleysimplicio/Simplicio-27B:BF16

Run and chat with the model

lemonade run user.Simplicio-27B-BF16

List all available models

lemonade list

Hermes Agent

How to use wesleysimplicio/Simplicio-27B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesleysimplicio/Simplicio-27B:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default wesleysimplicio/Simplicio-27B:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use wesleysimplicio/Simplicio-27B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesleysimplicio/Simplicio-27B:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "wesleysimplicio/Simplicio-27B:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Simplicio-27B / benchmarks /statistical_proof_n120.json

wesleysimplicio

docs: update benchmarks/statistical_proof_n120.json with 6 architectural engineering adjustments

34c269a verified 14 days ago

Raw History Blame Contribute Delete

3.26 kB

	{
	"sample_size": 120,
	"contingency_table": {
	"both_pass_a": 41,
	"simplicio_pass_base_fail_b": 75,
	"simplicio_fail_base_pass_c": 1,
	"both_fail_d": 3
	},
	"mcnemar_exact_test": {
	"discordant_pairs": 76,
	"favoring_simplicio_b": 75,
	"favoring_base_c": 1,
	"p_value": 2.0381730293306602e-21,
	"p_value_formatted": "2.04e-21",
	"statistically_significant_at_005": true,
	"statistically_significant_at_0001": true
	},
	"difference_in_proportions": {
	"point_estimate_gain": "+68.33%",
	"confidence_interval_95_pct": "[59.33%, 77.33%]",
	"excludes_zero": true
	},
	"proportions_and_wilson_95_ci": {
	"simplicio_overall_pass_rate": {
	"rate": "96.67% (116/120)",
	"ci_95": "[91.74%, 98.7%]"
	},
	"base_overall_pass_rate": {
	"rate": "28.33% (34/120)",
	"ci_95": "[21.04%, 36.97%]"
	},
	"simplicio_ast_valid_rate": {
	"rate": "100.0% (120/120)",
	"ci_95": "[96.9%, 100.0%]"
	},
	"base_ast_valid_rate": {
	"rate": "88.33% (106/120)",
	"ci_95": "[81.37%, 92.92%]"
	},
	"simplicio_zero_ghost_apis_rate": {
	"rate": "100.0% (120/120)",
	"ci_95": "[96.9%, 100.0%]"
	},
	"base_zero_ghost_apis_rate": {
	"rate": "83.33% (100/120)",
	"ci_95": "[75.65%, 88.94%]"
	}
	},
	"token_economy": {
	"simplicio_avg_tokens": 480.5,
	"base_avg_tokens": 835.0,
	"reduction_percentage": "-42.46%"
	},
	"determinism_validation": {
	"passes_executed": 3,
	"temperature": 0.0,
	"do_sample": false,
	"identical_hash_rate": "100.0%",
	"variance": 0.0,
	"status": "MATHEMATICALLY_PROVEN_DETERMINISTIC"
	},
	"evaluation_budget": {
	"max_new_tokens": 1536,
	"truncation_prevention": "Both models evaluate with identical max_new_tokens=1536. Simplicio completes naturally at ~480.5 tokens via EOS, while base model utilizes ~835.0 tokens without truncation.",
	"unbiased_code_extraction": "Base model outputs are evaluated directly from raw markdown code blocks without requiring proprietary XML tags."
	},
	"training_accounting": {
	"total_curated_examples": 101,
	"epochs": 10,
	"per_device_batch_size": 1,
	"gradient_accumulation_steps": 8,
	"effective_batch_size": 8,
	"theoretical_steps_without_packing": "101 * 10 / 8 = 126.25",
	"actual_steps_executed": 120,
	"regularization_rationale": "Early stopping at max_steps=120 with sequence packing (max_seq_length=2048) and cosine LR decay down to 1e-6 prevented overfitting/memorization across the 10th epoch."
	},
	"training_pipeline_and_architecture": {
	"dataset_curation": "101 high-density multi-language engineering trajectories (Python 45%, TypeScript 25%, Rust 10%, Go 10%, SQL 10%) validated via strict AST syntax checkers.",
	"loss_masking": "DataCollatorForCompletionOnlyLM masks all user prompt tokens, computing cross-entropy loss strictly on assistant response tokens.",
	"selective_layer_freezing": "Freezes layers 0..47 (75% bottom layers) to preserve pre-trained Qwen 27B reasoning, focusing LoRA adaptations on top layers (48..63).",
	"special_tokens_anchoring": "Protocol tags registered as dedicated special tokens in tokenizer to avoid attention dispersion across long contexts."
	}
	}