Instructions to use Convergent-ch/Pico-1.3-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Convergent-ch/Pico-1.3-Math with Transformers:

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

pipe = pipeline("text-generation", model="Convergent-ch/Pico-1.3-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Convergent-ch/Pico-1.3-Math")
model = AutoModelForCausalLM.from_pretrained("Convergent-ch/Pico-1.3-Math", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Convergent-ch/Pico-1.3-Math 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 Convergent-ch/Pico-1.3-Math
# Run inference directly in the terminal:
llama cli -hf Convergent-ch/Pico-1.3-Math

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Convergent-ch/Pico-1.3-Math
# Run inference directly in the terminal:
llama cli -hf Convergent-ch/Pico-1.3-Math

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 Convergent-ch/Pico-1.3-Math
# Run inference directly in the terminal:
./llama-cli -hf Convergent-ch/Pico-1.3-Math

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 Convergent-ch/Pico-1.3-Math
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Convergent-ch/Pico-1.3-Math

Use Docker

docker model run hf.co/Convergent-ch/Pico-1.3-Math

Llama new
LM Studio
Jan

vLLM

How to use Convergent-ch/Pico-1.3-Math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Convergent-ch/Pico-1.3-Math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Convergent-ch/Pico-1.3-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Convergent-ch/Pico-1.3-Math

SGLang

How to use Convergent-ch/Pico-1.3-Math 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 "Convergent-ch/Pico-1.3-Math" \
    --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": "Convergent-ch/Pico-1.3-Math",
		"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 "Convergent-ch/Pico-1.3-Math" \
        --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": "Convergent-ch/Pico-1.3-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Convergent-ch/Pico-1.3-Math with Ollama:
```
ollama run hf.co/Convergent-ch/Pico-1.3-Math
```
Unsloth Desktop
Docker Model Runner
How to use Convergent-ch/Pico-1.3-Math with Docker Model Runner:
```
docker model run hf.co/Convergent-ch/Pico-1.3-Math
```

Lemonade

How to use Convergent-ch/Pico-1.3-Math with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Convergent-ch/Pico-1.3-Math

Run and chat with the model

lemonade run user.Pico-1.3-Math-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Pico-1.3-Math

File size: 2,335 Bytes

ffef6a1

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "model_type": "llama",
  "vocab_size": 512,
  "hidden_size": 288,
  "intermediate_size": 768,
  "num_hidden_layers": 8,
  "num_attention_heads": 6,
  "num_key_value_heads": 6,
  "head_dim": 48,
  "max_position_embeddings": 1024,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000,
  "hidden_act": "silu",
  "tie_word_embeddings": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "torch_dtype": "bfloat16",
  "attention_dropout": 0.0,
  "attention_bias": false,
  "mlp_bias": false,
  "makeai": {
    "id": "makeai://convergent/pico-1.3-math/1.3",
    "name": "Pico 1.3-Math",
    "version": "1.3",
    "description": "Pico 1.3-Math: ~8M-Parameter-Modell von Null. Rechnet Schritt f\u00fcr Schritt (+ - * /, Klammern, Prozent) und l\u00f6st einfache englische Textaufgaben. Jede Ziffer ist ein eigenes Token. Made by Convergent.",
    "tags": [
      "slm",
      "math",
      "pico"
    ],
    "icon": "\ud83e\uddee",
    "creator": {
      "name": "Convergent",
      "username": "convergent"
    },
    "original_creator": {
      "name": "Convergent",
      "username": "convergent"
    },
    "imported_by": [],
    "created": "2026-10-23T20:34:21+0200",
    "updated": "2026-10-23T21:53:25+0200",
    "param_count": 8114976,
    "context_length": 1024,
    "format": "makeai",
    "architecture_summary": {
      "layers": 8,
      "hidden": 288,
      "heads": 6,
      "kv_heads": 6,
      "attention": "MHA",
      "activation": "swiglu",
      "norm": "rmsnorm",
      "positional": "rope",
      "vocab": 512,
      "context": 1024,
      "source": "makeai"
    },
    "required_hardware": {
      "inference_bf16_gb": 0.42,
      "inference_int8_gb": 0.42,
      "inference_nf4_gb": 0.41,
      "full_training_gb": 1.1
    },
    "provenance": [
      {
        "event": "created",
        "by": "convergent",
        "at": "2026-10-23T20:34:21+0200",
        "method": "from_scratch"
      },
      {
        "event": "trained",
        "run": "run-20261023-203431-938fd6",
        "steps": 9000,
        "at": "2026-10-23T21:53:25+0200",
        "method": "from_scratch"
      }
    ],
    "method": "from_scratch",
    "base_model": null,
    "license": ""
  }
}